OCR.md

OCR

Title	Date	Abstract	Comment	CodeRepository
A Benchmark of State-Space Models vs. Transformers and BiLSTM-based Models for Historical Newspaper OCR	2026-04-01	Show End-to-end OCR for historical newspapers remains challenging, as models must handle long text sequences, degraded print quality, and complex layouts. While Transformer-based recognizers dominate current research, their quadratic complexity limits efficient paragraph-level transcription and large-scale deployment. We investigate linear-time State-Space Models (SSMs), specifically Mamba, as a scalable alternative to Transformer-based sequence modeling for OCR. We present to our knowledge, the first OCR architecture based on SSMs, combining a CNN visual encoder with bi-directional and autoregressive Mamba sequence modeling, and conduct a large-scale benchmark comparing SSMs with Transformer- and BiLSTM-based recognizers. Multiple decoding strategies (CTC, autoregressive, and non-autoregressive) are evaluated under identical training conditions alongside strong neural baselines (VAN, DAN, DANIEL) and widely used off-the-shelf OCR engines (PERO-OCR, Tesseract OCR, TrOCR, Gemini). Experiments on historical newspapers from the Bibliothèque nationale du Luxembourg, with newly released >99% verified gold-standard annotations, and cross-dataset tests on Fraktur and Antiqua lines, show that all neural models achieve low error rates (~2% CER), making computational efficiency the main differentiator. Mamba-based models maintain competitive accuracy while halving inference time and exhibiting superior memory scaling (1.26x vs 2.30x growth at 1000 chars), reaching 6.07% CER at the severely degraded paragraph level compared to 5.24% for DAN, while remaining 2.05x faster. We release code, trained models, and standardized evaluation protocols to enable reproducible research and guide practitioners in large-scale cultural heritage OCR.		None
Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models	2026-03-31	Show Optical Character Recognition (OCR) is increasingly regarded as a foundational capability for modern vision-language models (VLMs), enabling them not only to read text in images but also to support downstream reasoning in real-world visual question answering (VQA). However, practical applications further require reliable text anchors, i.e., accurately grounding queried text to its corresponding spatial region. To systematically evaluate this capability, we introduce TextAnchor-Bench (TABench), a benchmark for fine-grained text-region grounding, which reveals that both general-purpose and OCR-specific VLMs still struggle to establish accurate and stable text anchors. To address this limitation, we propose Q-Mask, a precise OCR framework built upon a causal query-driven mask decoder (CQMD). Inspired by chain-of-thought reasoning, Q-Mask performs causal visual decoding that sequentially generates query-conditioned visual masks before producing the final OCR output. This visual CoT paradigm disentangles where the text is from what the text is, enforcing grounded evidence acquisition prior to recognition and enabling explicit text anchor construction during inference. To train CQMD, we construct TextAnchor-26M, a large-scale dataset of image-text pairs annotated with fine-grained masks corresponding to specific textual elements, encouraging stable text-region correspondences and injecting strong spatial priors into VLM training. Extensive experiments demonstrate that Q-Mask substantially improves text anchoring and understanding across diverse visual scenes.		None
From Plausibility to Verifiability: Risk-Controlled Generative OCR for Vision-Language Models	2026-03-31	Show Modern vision-language models (VLMs) can act as generative OCR engines, yet open-ended decoding can expose rare but consequential failures. We identify a core deployment misalignment in generative OCR. Autoregressive decoding favors semantic plausibility, whereas OCR requires outputs that are visually grounded and geometrically verifiable. This mismatch produces severe errors, especially over-generation and unsupported substitutions, creating deployment risk even when benchmark accuracy remains high. We therefore formulate frozen VLM OCR as a selective accept/abstain problem and propose a model-agnostic Geometric Risk Controller. The controller probes multiple structured views of the same input, applies lightweight structural screening, and accepts a transcription only when cross-view consensus and stability satisfy predefined criteria, yielding a small family of operating points. Experiments on frozen VLM backbones and standard OCR benchmarks show consistent reductions in extreme-error risk and catastrophic over-generation at predictable coverage costs. Reliable deployment of generative OCR with frozen VLMs benefits from explicit system-level risk control rather than unconstrained generation.	10 pa... 10 pages, 5 figures, 5 tables	None
A Survey of OCR Evaluation Methods and Metrics and the Invisibility of Historical Documents	2026-03-26	Show Optical character recognition (OCR) and document understanding systems increasingly rely on large vision and vision-language models, yet evaluation remains centered on modern, Western, and institutional documents. This emphasis masks system behavior in historical and marginalized archives, where layout, typography, and material degradation shape interpretation. This study examines how OCR and document understanding systems are evaluated, with particular attention to Black historical newspapers. We review OCR and document understanding papers, as well as benchmark datasets, which are published between 2006 and 2025 using the PRISMA framework. We look into how the studies report training data, benchmark design, and evaluation metrics for vision transformer and multimodal OCR systems. During the review, we found that Black newspapers and other community-produced historical documents rarely appear in reported training data or evaluation benchmarks. Most evaluations emphasize character accuracy and task success on modern layouts. They rarely capture structural failures common in historical newspapers, including column collapse, typographic errors, and hallucinated text. To put these findings into perspective, we use previous empirical studies and archival statistics from significant Black press collections to show how evaluation gaps lead to structural invisibility and representational harm. We propose that these gaps occur due to organizational (meso) and institutional (macro) behaviors and structure, shaped by benchmark incentives and data governance decisions.	This ... This manuscript is the author's submitted version to the ACM Conference on Fairness, Accountability, and Transparency (FAccT 2026). Please cite the final published version via ACM Digital Library when available	None
PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks	2026-03-25	Show The advent of "OCR 2.0" and large-scale vision-language models (VLMs) has set new benchmarks in text recognition. However, these unified architectures often come with significant computational demands, challenges in precise text localization within complex layouts, and a propensity for textual hallucinations. Revisiting the prevailing notion that model scale is the sole path to high accuracy, this paper introduces PP-OCRv5, a meticulously optimized, lightweight OCR system with merely 5 million parameters. We demonstrate that PP-OCRv5 achieves performance competitive with many billion-parameter VLMs on standard OCR benchmarks, while offering superior localization precision and reduced hallucinations. The cornerstone of our success lies not in architectural expansion but in a data-centric investigation. We systematically dissect the role of training data by quantifying three critical dimensions: data difficulty, data accuracy, and data diversity. Our extensive experiments reveal that with a sufficient volume of high-quality, accurately labeled, and diverse data, the performance ceiling for traditional, efficient two-stage OCR pipelines is far higher than commonly assumed. This work provides compelling evidence for the viability of lightweight, specialized models in the large-model era and offers practical insights into data curation for OCR. The source code and models are publicly available at https://github.com/PaddlePaddle/PaddleOCR.		Code Link
MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding	2026-03-23	Show Optical character recognition (OCR) has evolved from line-level transcription to structured document parsing, requiring models to recover long-form sequences containing layout, tables, and formulas. Despite recent advances in vision-language models, most existing systems rely on autoregressive decoding, which introduces sequential latency and amplifies error propagation in long documents. In this work, we revisit document OCR from an inverse rendering perspective, arguing that left-to-right causal generation is an artifact of serialization rather than an intrinsic property of the task. Motivated by this insight, we propose MinerU-Diffusion, a unified diffusion-based framework that replaces autoregressive sequential decoding with parallel diffusion denoising under visual conditioning. MinerU-Diffusion employs a block-wise diffusion decoder and an uncertainty-driven curriculum learning strategy to enable stable training and efficient long-sequence inference. Extensive experiments demonstrate that MinerU-Diffusion consistently improves robustness while achieving up to 3.2x faster decoding compared to autoregressive baselines. Evaluations on the proposed Semantic Shuffle benchmark further confirm its reduced dependence on linguistic priors and stronger visual OCR capability.		None
OCRGenBench: A Comprehensive Benchmark for Evaluating OCR Generative Capabilities	2026-03-20	Show Improving visual text synthesis has long been a challenging and evolving frontier for image generation models. While recent state-of-the-art (SOTA) models have made remarkable strides in text generation capabilities, existing benchmarks inadequately assess their true performance due to narrow scope (scene text and posters only), isolated evaluation (T2I generation or editing separately), and insufficient difficulty (lacking challenging scenarios). To bridge this gap, we pioneer the unification of text-centric T2I generation, text editing, and OCR-related image-to-image translation to evaluate a model's holistic visual text synthesis abilities, i.e., OCR generative capabilities. Accordingly, we propose OCRGenBench, the most comprehensive benchmark to date for evaluating these abilities. OCRGenBench covers five common text categories and 33 OCR generative tasks, encompassing T2I generation, text editing, and other image-to-image OCR tasks (e.g., document dewarping and handwriting removal). The benchmark includes 1,060 human-annotated samples consisting of instruction-image-GT triplets, deliberately featuring high text density, diverse generation scales, varied aspect ratios, and bilingual content to capture real-world complexity. Furthermore, we introduce OCRGenScore, a unified metric integrating text accuracy, aesthetic quality, and instruction following. Extensive experiments on 19 cutting-edge generative models reveal that most score below 60/100. Our analysis exposes critical, previously overlooked limitations, including poor text localization, unintended content modifications, and failures with dense or small-scale text. We hope OCRGenBench establishes a robust standard to evaluate OCR generative capabilities, driving the evolution of reliable visual text synthesis. The benchmark and evaluation code are available at https://github.com/NiceRingNode/Awesome-Generative-Models-for-OCR.		Code Link
Detached Skip-Links and $R$-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCR	2026-03-20	Show Multimodal large language models (MLLMs) excel at high-level reasoning yet fail on OCR tasks where fine-grained visual details are compromised or misaligned. We identify an overlooked optimization issue in multi-layer feature fusion. Skip pathways introduce direct back-propagation paths from high-level semantic objectives to early visual layers. This mechanism overwrites low-level signals and destabilizes training. To mitigate this gradient interference, we propose Detached Skip-Links, a minimal modification that reuses shallow features in the forward pass while stopping gradients through the skip branch during joint training. This asymmetric design reduces gradient interference, improving stability and convergence without adding learnable parameters. To diagnose whether fine-grained information is preserved and usable by an LLM, we introduce $R$-Probe, which measures pixel-level reconstructability of projected visual tokens using a shallow decoder initialized from the first quarter of the LLM layers. Across multiple ViT backbones and multimodal benchmarks, and at scales up to 7M training samples, our approach consistently improves OCR-centric benchmarks and delivers clear gains on general multimodal tasks.		None
Automated Wicket-Taking Delivery Segmentation and Trajectory-Based Dismissal-Zone Analysis in Cricket Videos Using OCR-Guided YOLOv8	2026-03-18	Show Cricket generates a rich stream of visual and contextual information, yet much of its tactical analysis still depends on slow and subjective manual review. Motivated by the need for a more efficient and data-driven alternative, this paper presents an automated approach for cricket video analysis that identifies wicket-taking deliveries, detects the pitch and ball, and models ball trajectories for post-match assessment. The proposed system combines optical character recognition (OCR) with image preprocessing techniques, including grayscale conversion, power transformation, and morphological operations, to robustly extract scorecard information and detect wicket events from broadcast videos. For visual understanding, YOLOv8 is employed for both pitch and ball detection. The pitch detection model achieved 99.5% mAP50 with a precision of 0.999, while the transfer learning-based ball detection model attained 99.18% mAP50 with 0.968 precision and 0.978 recall. Based on these detections, the system further models ball trajectories to reveal regions associated with wicket-taking deliveries, offering analytical cues for trajectory-based dismissal-zone interpretation and potential batting vulnerability assessment. Experimental results on multiple cricket match videos demonstrate the effectiveness of the proposed approach and highlight its potential for supporting coaching, tactical evaluation, and data-driven decision-making in cricket.	3 fig... 3 figures, 5 tables, submitted to the IEEE International Conference on Engineering and Frontier Technologies (ICEFronT) 2026	None
KidsNanny: A Two-Stage Multimodal Content Moderation Pipeline Integrating Visual Classification, Object Detection, OCR, and Contextual Reasoning for Child Safety	2026-03-17	Show We present KidsNanny, a two-stage multimodal content moderation architecture for child safety. Stage 1 combines a vision transformer (ViT) with an object detector for visual screening (11.7 ms); outputs are routed as text not raw pixels to Stage 2, which applies OCR and a text based 7B language model for contextual reasoning (120 ms total pipeline). We evaluate on the UnsafeBench Sexual category (1,054 images) under two regimes: vision-only, isolating Stage 1, and multimodal, evaluating the full Stage 1+2 pipeline. Stage 1 achieves 80.27% accuracy and 85.39% F1 at 11.7 ms; vision-only baselines range from 59.01% to 77.04% accuracy. The full pipeline achieves 81.40% accuracy and 86.16% F1 at 120 ms, compared to ShieldGemma-2 (64.80% accuracy, 1,136 ms) and LlavaGuard (80.36% accuracy, 4,138 ms). To evaluate text-awareness, we filter two subsets: a text+visual subset (257 images) and a text-only subset (44 images where safety depends primarily on embedded text). On text-only images, KidsNanny achieves 100% recall (25/25 positives; small sample) and 75.76% precision; ShieldGemma-2 achieves 84% recall and 60% precision at 1,136 ms. Results suggest that dedicated OCR-based reasoning may offer recall-precision advantages on text-embedded threats at lower latency, though the small text-only subset limits generalizability. By documenting this architecture and evaluation methodology, we aim to contribute to the broader research effort on efficient multimodal content moderation for child safety.	12 pa... 12 pages, 2 figures, 6 tables	None
Multimodal OCR: Parse Anything from Documents	2026-03-13	Show We present Multimodal OCR (MOCR), a document parsing paradigm that jointly parses text and graphics into unified textual representations. Unlike conventional OCR systems that focus on text recognition and leave graphical regions as cropped pixels, our method, termed dots.mocr, treats visual elements such as charts, diagrams, tables, and icons as first-class parsing targets, enabling systems to parse documents while preserving semantic relationships across elements. It offers several advantages: (1) it reconstructs both text and graphics as structured outputs, enabling more faithful document reconstruction; (2) it supports end-to-end training over heterogeneous document elements, allowing models to exploit semantic relations between textual and visual components; and (3) it converts previously discarded graphics into reusable code-level supervision, unlocking multimodal supervision embedded in existing documents. To make this paradigm practical at scale, we build a comprehensive data engine from PDFs, rendered webpages, and native SVG assets, and train a compact 3B-parameter model through staged pretraining and supervised fine-tuning. We evaluate dots.mocr from two perspectives: document parsing and structured graphics parsing. On document parsing benchmarks, it ranks second only to Gemini 3 Pro on our OCR Arena Elo leaderboard, surpasses existing open-source document parsing systems, and sets a new state of the art of 83.9 on olmOCR Bench. On structured graphics parsing, dots.mocr achieves higher reconstruction quality than Gemini 3 Pro across image-to-SVG benchmarks, demonstrating strong performance on charts, UI layouts, scientific figures, and chemical diagrams. These results show a scalable path toward building large-scale image-to-code corpora for multimodal pretraining. Code and models are publicly available at https://github.com/rednote-hilab/dots.mocr.		Code Link
Qianfan-OCR: A Unified End-to-End Model for Document Intelligence	2026-03-11	Show We present Qianfan-OCR, a 4B-parameter end-to-end vision-language model that unifies document parsing, layout analysis, and document understanding within a single architecture. It performs direct image-to-Markdown conversion and supports diverse prompt-driven tasks including table extraction, chart understanding, document QA, and key information extraction. To address the loss of explicit layout analysis in end-to-end OCR, we propose Layout-as-Thought, an optional thinking phase triggered by special think tokens that generates structured layout representations -- bounding boxes, element types, and reading order -- before producing final outputs, recovering layout grounding capabilities while improving accuracy on complex layouts. Qianfan-OCR ranks first among end-to-end models on OmniDocBench v1.5 (93.12) and OlmOCR Bench (79.8), achieves competitive results on OCRBench, CCOCR, DocVQA, and ChartQA against general VLMs of comparable scale, and attains the highest average score on public key information extraction benchmarks, surpassing Gemini-3.1-Pro, Seed-2.0, and Qwen3-VL-235B. The model is publicly accessible via the Baidu AI Cloud Qianfan platform.		None
Agentar-Fin-OCR	2026-03-11	Show In this paper, we propose Agentar-Fin-OCR, a document parsing system tailored to financial-domain documents, transforming ultra-long financial PDFs into semantically consistent, highly accurate, structured outputs with auditing-grade provenance. To address finance-specific challenges such as complex layouts, cross-page structural discontinuities, and cell-level referencing capability, Agentar-Fin-OCR combines (1) a Cross-page Contents Consolidation algorithm to restore continuity across pages and a Document-level Heading Hierarchy Reconstruction (DHR) module to build a globally consistent Table of Contents (TOC) tree for structure-aware retrieval, and (2) a difficulty-adaptive curriculum learning training strategy for table parsing, together with a CellBBoxRegressor module that uses structural anchor tokens to localize table cells from decoder hidden states without external detectors. Experiments demonstrate that our model shows high performance on the table parsing metrics of OmniDocBench. To enable realistic evaluation in the financial vertical, we further introduce FinDocBench, a benchmark that includes six financial document categories with expert-verified annotations and evaluation metrics including Table of Contents edit-distance-based similarity (TocEDS), cross-page concatenated TEDS, and Table Cell Intersection over Union (C-IoU). We evaluate a wide range of state-of-the-art models on FinDocBench to assess their capabilities and remaining limitations on financial documents. Overall, Agentar-Fin-OCR and FinDocBench provide a practical foundation for reliable downstream financial document applications.		None
GLM-OCR Technical Report	2026-03-11	Show GLM-OCR is an efficient 0.9B-parameter compact multimodal model designed for real-world document understanding. It combines a 0.4B-parameter CogViT visual encoder with a 0.5B-parameter GLM language decoder, achieving a strong balance between computational efficiency and recognition performance. To address the inefficiency of standard autoregressive decoding in deterministic OCR tasks, GLM-OCR introduces a Multi-Token Prediction (MTP) mechanism that predicts multiple tokens per step, significantly improving decoding throughput while keeping memory overhead low through shared parameters. At the system level, a two-stage pipeline is adopted: PP-DocLayout-V3 first performs layout analysis, followed by parallel region-level recognition. Extensive evaluations on public benchmarks and industrial scenarios show that GLM-OCR achieves competitive or state-of-the-art performance in document parsing, text and formula transcription, table structure recovery, and key information extraction. Its compact architecture and structured generation make it suitable for both resource-constrained edge deployment and large-scale production systems.		None
The Patrologia Graeca Corpus: OCR, Annotation, and Open Release of Noisy Nineteenth-Century Polytonic Greek Editions	2026-03-10	Show We present the Patrologia Graeca Corpus, the first large-scale open OCR and linguistic resource for nineteenthcentury editions of Ancient Greek. The collection covers the remaining undigitized volumes of the Patrologia Graeca (PG), printed in complex bilingual (Greek-Latin) layouts and characterized by highly degraded polytonic Greek typography. Through a dedicated pipeline combining YOLO-based layout detection and CRNN-based text recognition, we achieve a character error rate (CER) of 1.05% and a word error rate (WER) of 4.69%, largely outperforming existing OCR systems for polytonic Greek. The resulting corpus contains around six million lemmatized and part-of-speech tagged tokens, aligned with full OCR and layout annotations. Beyond its philological value, this corpus establishes a new benchmark for OCR on noisy polytonic Greek and provides training material for future models, including LLMs.		None
Whispering to a Blackbox: Bootstrapping Frozen OCR with Visual Prompts	2026-03-05	Show In the landscape of modern machine learning, frozen pre-trained models provide stability and efficiency but often underperform on specific tasks due to mismatched data distributions. This paper introduces the Whisperer, a novel visual prompting framework that learns diffusion-based preprocessors to adapt inputs in pixel space, effectively "whispering" enhancements to frozen downstream models like EasyOCR. By framing the process as behavioral cloning of stochastically discovered improvement policies, our method achieves an 8% absolute (10.6% relative) reduction in Character Error Rate (CER) on a challenging dataset of 300k degraded synthetic text images, surpassing hand-engineered baselines such as CLAHE. The key innovation is a four-stage training curriculum that uses behavioral cloning to amplify "lucky" improvements discovered through the stochastic exploration of a partially trained diffusion model. This approach is highly sample-efficient and avoids the pitfalls of traditional reinforcement learning. Crucially, we frame this not as naive reinforcement learning, but as behavioral cloning of an exploration policy: we stochastically sample intermediate diffusion outputs, select those that improve CER by chance, and then train the model to reproduce them. This bootstrapping curriculum (4 stages over 60 GPU-hours) amplifies random successes into a systematic strategy. In summary, by whispering to the frozen OCR through its inputs, we improve an imperfect classifier without touching its weights.		None
From OCR to Analysis: Tracking Correction Provenance in Digital Humanities Pipelines	2026-03-03	Show Optical Character Recognition (OCR) is a critical but error-prone stage in digital humanities text pipelines. While OCR correction improves usability for downstream NLP tasks, common workflows often overwrite intermediate decisions, obscuring how textual transformations affect scholarly interpretation. We present a provenance-aware framework for OCR-corrected humanities corpora that records correction lineage at the span level, including edit type, correction source, confidence, and revision status. Using a pilot corpus of historical texts, we compare downstream named entity extraction across raw OCR, fully corrected text, and provenance-filtered corrections. Our results show that correction pathways can substantially alter extracted entities and document-level interpretations, while provenance signals help identify unstable outputs and prioritize human review. We argue that provenance should be treated as a first-class analytical layer in NLP for digital humanities, supporting reproducibility, source criticism, and uncertainty-aware interpretation.		None
OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale Datasets	2026-03-03	Show Multimodal Large Language Models (MLLMs) enhance the potential of natural language processing. However, their actual impact on document information extraction remains unclear. In particular, it is unclear whether an MLLM-only pipeline--while simpler--can truly match the performance of traditional OCR+MLLM setups. In this paper, we conduct a large-scale benchmarking study that evaluates various out-of-the-box MLLMs on business-document information extraction. To examine and explore failure modes, we propose an automated hierarchical error analysis framework that leverages large language models (LLMs) to diagnose error patterns systematically. Our findings suggest that OCR may not be necessary for powerful MLLMs, as image-only input can achieve comparable performance to OCR-enhanced approaches. Moreover, we demonstrate that carefully designed schema, exemplars, and instructions can further enhance MLLMs performance. We hope this work can offer practical guidance and valuable insight for advancing document information extraction.		None
FireRed-OCR Technical Report	2026-03-02	Show We present FireRed-OCR, a systematic framework to specialize general VLMs into high-performance OCR models. Large Vision-Language Models (VLMs) have demonstrated impressive general capabilities but frequently suffer from structural hallucination'' when processing complex documents, limiting their utility in industrial OCR applications. In this paper, we introduce FireRed-OCR, a novel framework designed to transform general-purpose VLMs (based on Qwen3-VL) into pixel-precise structural document parsing experts. To address the scarcity of high-quality structured data, we construct a Geometry + Semantics'' Data Factory. Unlike traditional random sampling, our pipeline leverages geometric feature clustering and multi-dimensional tagging to synthesize and curate a highly balanced dataset, effectively handling long-tail layouts and rare document types. Furthermore, we propose a Three-Stage Progressive Training strategy that guides the model from pixel-level perception to logical structure generation. This curriculum includes: (1) Multi-task Pre-alignment to ground the model's understanding of document structure; (2) Specialized SFT for standardizing full-image Markdown output; and (3) Format-Constrained Group Relative Policy Optimization (GRPO), which utilizes reinforcement learning to enforce strict syntactic validity and structural integrity (e.g., table closure, formula syntax). Extensive evaluations on OmniDocBench v1.5 demonstrate that FireRed-OCR achieves state-of-the-art performance with an overall score of 92.94%, significantly outperforming strong baselines such as DeepSeek-OCR 2 and OCRVerse across text, formula, table, and reading order metrics. We open-source our code and model weights to facilitate the ``General VLM to Specialized Structural Expert'' paradigm.		None
Where Vision Becomes Text: Locating the OCR Routing Bottleneck in Vision-Language Models	2026-02-26	Show Vision-language models (VLMs) can read text from images, but where does this optical character recognition (OCR) information enter the language processing stream? We investigate the OCR routing mechanism across three architecture families (Qwen3-VL, Phi-4, InternVL3.5) using causal interventions. By computing activation differences between original images and text-inpainted versions, we identify architecture-specific OCR bottlenecks whose dominant location depends on the vision-language integration strategy: DeepStack models (Qwen) show peak sensitivity at mid-depth (about 50%) for scene text, while single-stage projection models (Phi-4, InternVL) peak at early layers (6-25%), though the exact layer of maximum effect varies across datasets. The OCR signal is remarkably low-dimensional: PC1 captures 72.9% of variance. Crucially, principal component analysis (PCA) directions learned on one dataset transfer to others, demonstrating shared text-processing pathways. Surprisingly, in models with modular OCR circuits (notably Qwen3-VL-4B), OCR removal can improve counting performance (up to +6.9 percentage points), suggesting OCR interferes with other visual processing in sufficiently modular architectures.		None
OCR-Agent: Agentic OCR with Capability and Memory Reflection	2026-02-24	Show Large Vision-Language Models (VLMs) have demonstrated significant potential on complex visual understanding tasks through iterative optimization methods.However, these models generally lack effective self-correction mechanisms, making it difficult for them to independently rectify cognitive biases. Consequently, during multi-turn revisions, they often fall into repetitive and ineffective attempts, failing to achieve stable improvements in answer quality.To address this issue, we propose a novel iterative self-correction framework that endows models with two key capabilities: Capability Reflection and Memory Reflection. This framework guides the model to first diagnose errors and generate a correction plan via Capability Reflection, then leverage Memory Reflection to review past attempts to avoid repetition and explore new solutions, and finally, optimize the answer through rigorous re-reasoning. Experiments on the challenging OCRBench v2 benchmark show that OCR-Agent outperforms the current open-source SOTA model InternVL3-8B by +2.0 on English and +1.2 on Chinese subsets, while achieving state-of-the-art results in Visual Understanding (79.9) and Reasoning (66.5) - surpassing even larger fine-tuned models. Our method demonstrates that structured, self-aware reflection can significantly enhance VLMs' reasoning robustness without additional training. Code: https://github.com/AIGeeksGroup/OCR-Agent.		Code Link
OmniOCR: Generalist OCR for Ethnic Minority Languages	2026-02-24	Show Optical character recognition (OCR) has advanced rapidly with deep learning and multimodal models, yet most methods focus on well-resourced scripts such as Latin and Chinese. Ethnic minority languages remain underexplored due to complex writing systems, scarce annotations, and diverse historical and modern forms, making generalization in low-resource or zero-shot settings challenging. To address these challenges, we present OmniOCR, a universal framework for ethnic minority scripts. OmniOCR introduces Dynamic Low-Rank Adaptation (Dynamic LoRA) to allocate model capacity across layers and scripts, enabling effective adaptation while preserving knowledge.A sparsity regularization prunes redundant updates, ensuring compact and efficient adaptation without extra inference cost. Evaluations on TibetanMNIST, Shui, ancient Yi, and Dongba show that OmniOCR outperforms zero-shot foundation models and standard post training, achieving state-of-the-art accuracy with superior parameter efficiency, and compared with the state-of-the-art baseline models, it improves accuracy by 39%-66% on these four datasets. Code: https://github.com/AIGeeksGroup/OmniOCR.		Code Link
DODO: Discrete OCR Diffusion Models	2026-02-18	Show Optical Character Recognition (OCR) is a fundamental task for digitizing information, serving as a critical bridge between visual data and textual understanding. While modern Vision-Language Models (VLM) have achieved high accuracy in this domain, they predominantly rely on autoregressive decoding, which becomes computationally expensive and slow for long documents as it requires a sequential forward pass for every generated token. We identify a key opportunity to overcome this bottleneck: unlike open-ended generation, OCR is a highly deterministic task where the visual input strictly dictates a unique output sequence, theoretically enabling efficient, parallel decoding via diffusion models. However, we show that existing masked diffusion models fail to harness this potential; those introduce structural instabilities that are benign in flexible tasks, like captioning, but catastrophic for the rigid, exact-match requirements of OCR. To bridge this gap, we introduce DODO, the first VLM to utilize block discrete diffusion and unlock its speedup potential for OCR. By decomposing generation into blocks, DODO mitigates the synchronization errors of global diffusion. Empirically, our method achieves near state-of-the-art accuracy while enabling up to 3x faster inference compared to autoregressive baselines.		None
Designing Production-Scale OCR for India: Multilingual and Domain-Specific Systems	2026-02-18	Show Designing Optical Character Recognition (OCR) systems for India requires balancing linguistic diversity, document heterogeneity, and deployment constraints. In this paper, we study two training strategies for building multilingual OCR systems with Vision-Language Models through the Chitrapathak series. We first follow a popular multimodal approach, pairing a generic vision encoder with a strong multilingual language model and training the system end-to-end for OCR. Alternatively, we explore fine-tuning an existing OCR model, despite not being trained for the target languages. Through extensive evaluation on multilingual Indic OCR benchmarks and deployment-oriented metrics, we find that the second strategy consistently achieves better accuracy-latency trade-offs. Chitrapathak-2 achieves 3-6x speedup over its predecessor with being state-of-the-art (SOTA) in Telugu (6.69 char ANLS) and second best in the rest. In addition, we present Parichay, an independent OCR model series designed specifically for 9 Indian government documents to extract structured key fields, achieving 89.8% Exact Match score with a faster inference. Together, these systems achieve SOTA performance and provide practical guidance for building production-scale OCR pipelines in the Indian context.		None
KazakhOCR: A Synthetic Benchmark for Evaluating Multimodal Models in Low-Resource Kazakh Script OCR	2026-02-17	Show Kazakh is a Turkic language using the Arabic, Cyrillic, and Latin scripts, making it unique in terms of optical character recognition (OCR). Work on OCR for low-resource Kazakh scripts is very scarce, and no OCR benchmarks or images exist for the Arabic and Latin scripts. We construct a synthetic OCR dataset of 7,219 images for all three scripts with font, color, and noise variations to imitate real OCR tasks. We evaluated three multimodal large language models (MLLMs) on a subset of the benchmark for OCR and language identification: Gemma-3-12B-it, Qwen2.5-VL-7B-Instruct, and Llama-3.2-11B-Vision-Instruct. All models are unsuccessful with Latin and Arabic script OCR, and fail to recognize the Arabic script as Kazakh text, misclassifying it as Arabic, Farsi, and Kurdish. We further compare MLLMs with a classical OCR baseline and find that while traditional OCR has lower character error rates, MLLMs fail to match this performance. These findings show significant gaps in current MLLM capabilities to process low-resource Abjad-based scripts and demonstrate the need for inclusive models and benchmarks supporting low-resource scripts and languages.	Accep... Accepted to AbjadNLP @ EACL 2026	None
Error Patterns in Historical OCR: A Comparative Analysis of TrOCR and a Vision-Language Model	2026-02-16	Show Optical Character Recognition (OCR) of eighteenth-century printed texts remains challenging due to degraded print quality, archaic glyphs, and non-standardized orthography. Although transformer-based OCR systems and Vision-Language Models (VLMs) achieve strong aggregate accuracy, metrics such as Character Error Rate (CER) and Word Error Rate (WER) provide limited insight into their reliability for scholarly use. We compare a dedicated OCR transformer (TrOCR) and a general-purpose Vision-Language Model (Qwen) on line-level historical English texts using length-weighted accuracy metrics and hypothesis driven error analysis. While Qwen achieves lower CER/WER and greater robustness to degraded input, it exhibits selective linguistic regularization and orthographic normalization that may silently alter historically meaningful forms. TrOCR preserves orthographic fidelity more consistently but is more prone to cascading error propagation. Our findings show that architectural inductive biases shape OCR error structure in systematic ways. Models with similar aggregate accuracy can differ substantially in error locality, detectability, and downstream scholarly risk, underscoring the need for architecture-aware evaluation in historical digitization workflows.		None
OCRTurk: A Comprehensive OCR Benchmark for Turkish	2026-02-03	Show Document parsing is now widely used in applications, such as large-scale document digitization, retrieval-augmented generation, and domain-specific pipelines in healthcare and education. Benchmarking these models is crucial for assessing their reliability and practical robustness. Existing benchmarks mostly target high-resource languages and provide limited coverage for low-resource settings, such as Turkish. Moreover, existing studies on Turkish document parsing lack a standardized benchmark that reflects real-world scenarios and document diversity. To address this gap, we introduce OCRTurk, a Turkish document parsing benchmark covering multiple layout elements and document categories at three difficulty levels. OCRTurk consists of 180 Turkish documents drawn from academic articles, theses, slide decks, and non-academic articles. We evaluate seven OCR models on OCRTurk using element-wise metrics. Across difficulty levels, PaddleOCR achieves the strongest overall results, leading most element-wise metrics except figures and attaining high Normalized Edit Distance scores in easy, medium, and hard subsets. We also observe performance variation by document type. Models perform well on non-academic documents, while slideshows become the most challenging.	Accep... Accepted by EACL 2026 SIGTURK	None
Evaluating OCR Performance for Assistive Technology: Effects of Walking Speed, Camera Placement, and Camera Type	2026-02-02	Show Optical character recognition (OCR), which converts printed or handwritten text into machine-readable form, is widely used in assistive technology for people with blindness and low vision. Yet, most evaluations rely on static datasets that do not reflect the challenges of mobile use. In this study, we systematically evaluated OCR performance under both static and dynamic conditions. Static tests measured detection range across distances of 1-7 meters and viewing angles of 0-75 degrees horizontally. Dynamic tests examined the impact of motion by varying walking speed from slow (0.8 m/s) to very fast (1.8 m/s) and comparing three camera mounting positions: head-mounted, shoulder-mounted, and hand-held. We evaluated both a smartphone and smart glasses, using the phone's main and ultra-wide cameras. Four OCR engines were benchmarked to assess accuracy at different distances and viewing angles: Google Vision, PaddleOCR 3.0, EasyOCR, and Tesseract. PaddleOCR 3.0 was then used to evaluate accuracy at different walking speeds. Accuracy was computed at the character level using the Levenshtein ratio against manually defined ground truth. Results showed that recognition accuracy declined with increased walking speed and wider viewing angles. Google Vision achieved the highest overall accuracy, with PaddleOCR close behind as the strongest open-source alternative. Across devices, the phone's main camera achieved the highest accuracy, and a shoulder-mounted placement yielded the highest average among body positions; however, differences among shoulder, head, and hand were not statistically significant.		None
OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models	2026-01-29	Show The development of large vision language models drives the demand for managing, and applying massive amounts of multimodal data, making OCR technology, which extracts information from visual images, increasingly popular. However, existing OCR methods primarily focus on recognizing text elements from images or scanned documents (\textbf{Text-centric OCR}), neglecting the identification of visual elements from visually information-dense image sources (\textbf{Vision-centric OCR}), such as charts, web pages and science plots. In reality, these visually information-dense images are widespread on the internet and have significant real-world application value, such as data visualization and web page analysis. In this technical report, we propose \textbf{OCRVerse}, the first holistic OCR method in end-to-end manner that enables unified text-centric OCR and vision-centric OCR. To this end, we constructe comprehensive data engineering to cover a wide range of text-centric documents, such as newspapers, magazines and books, as well as vision-centric rendered composites, including charts, web pages and scientific plots. Moreover, we propose a two-stage SFT-RL multi-domain training method for OCRVerse. SFT directly mixes cross-domain data to train and establish initial domain knowledge, while RL focuses on designing personalized reward strategies for the characteristics of each domain. Specifically, since different domains require various output formats and expected outputs, we provide sufficient flexibility in the RL stage to customize flexible reward signals for each domain, thereby improving cross-domain fusion and avoiding data conflicts. Experimental results demonstrate the effectiveness of OCRVerse, achieving competitive results across text-centric and vision-centric data types, even comparable to large-scale open-source and closed-source models.		None
DeepSeek-OCR 2: Visual Causal Flow	2026-01-28	Show We present DeepSeek-OCR 2 to investigate the feasibility of a novel encoder-DeepEncoder V2-capable of dynamically reordering visual tokens upon image semantics. Conventional vision-language models (VLMs) invariably process visual tokens in a rigid raster-scan order (top-left to bottom-right) with fixed positional encoding when fed into LLMs. However, this contradicts human visual perception, which follows flexible yet semantically coherent scanning patterns driven by inherent logical structures. Particularly for images with complex layouts, human vision exhibits causally-informed sequential processing. Inspired by this cognitive mechanism, DeepEncoder V2 is designed to endow the encoder with causal reasoning capabilities, enabling it to intelligently reorder visual tokens prior to LLM-based content interpretation. This work explores a novel paradigm: whether 2D image understanding can be effectively achieved through two-cascaded 1D causal reasoning structures, thereby offering a new architectural approach with the potential to achieve genuine 2D reasoning. Codes and model weights are publicly accessible at http://github.com/deepseek-ai/DeepSeek-OCR-2.		Code Link
synthocr-gen: A synthetic ocr dataset generator for low-resource languages- breaking the data barrier	2026-01-22	Show Optical Character Recognition (OCR) for low-resource languages remains a significant challenge due to the scarcity of large-scale annotated training datasets. Languages such as Kashmiri, with approximately 7 million speakers and a complex Perso-Arabic script featuring unique diacritical marks, currently lack support in major OCR systems including Tesseract, TrOCR, and PaddleOCR. Manual dataset creation for such languages is prohibitively expensive, time-consuming, and error-prone, often requiring word by word transcription of printed or handwritten text. We present SynthOCR-Gen, an open-source synthetic OCR dataset generator specifically designed for low-resource languages. Our tool addresses the fundamental bottleneck in OCR development by transforming digital Unicode text corpora into ready-to-use training datasets. The system implements a comprehensive pipeline encompassing text segmentation (character, word, n-gram, sentence, and line levels), Unicode normalization with script purity enforcement, multi-font rendering with configurable distribution, and 25+ data augmentation techniques simulating real-world document degradations including rotation, blur, noise, and scanner artifacts. We demonstrate the efficacy of our approach by generating a 600,000-sample word-segmented Kashmiri OCR dataset, which we release publicly on HuggingFace. This work provides a practical pathway for bringing low-resource languages into the era of vision-language AI models, and the tool is openly available for researchers and practitioners working with underserved writing systems worldwide.		None
Typhoon OCR: Open Vision-Language Model For Thai Document Extraction	2026-01-21	Show Document extraction is a core component of digital workflows, yet existing vision-language models (VLMs) predominantly favor high-resource languages. Thai presents additional challenges due to script complexity from non-latin letters, the absence of explicit word boundaries, and the prevalence of highly unstructured real-world documents, limiting the effectiveness of current open-source models. This paper presents Typhoon OCR, an open VLM for document extraction tailored for Thai and English. The model is fine-tuned from vision-language backbones using a Thai-focused training dataset. The dataset is developed using a multi-stage data construction pipeline that combines traditional OCR, VLM-based restructuring, and curated synthetic data. Typhoon OCR is a unified framework capable of text transcription, layout reconstruction, and document-level structural consistency. The latest iteration of our model, Typhoon OCR V1.5, is a compact and inference-efficient model designed to reduce reliance on metadata and simplify deployment. Comprehensive evaluations across diverse Thai document categories, including financial reports, government forms, books, infographics, and handwritten documents, show that Typhoon OCR achieves performance comparable to or exceeding larger frontier proprietary models, despite substantially lower computational cost. The results demonstrate that open vision-language OCR models can achieve accurate text extraction and layout reconstruction for Thai documents, reaching performance comparable to proprietary systems while remaining lightweight and deployable.		None
LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR	2026-01-20	Show We present \textbf{LightOnOCR-2-1B}, a 1B-parameter end-to-end multilingual vision--language model that converts document images (e.g., PDFs) into clean, naturally ordered text without brittle OCR pipelines. Trained on a large-scale, high-quality distillation mix with strong coverage of scans, French documents, and scientific PDFs, LightOnOCR-2 achieves state-of-the-art results on OlmOCR-Bench while being 9$\times$ smaller and substantially faster than prior best-performing models. We further extend the output format to predict normalized bounding boxes for embedded images, introducing localization during pretraining via a resume strategy and refining it with RLVR using IoU-based rewards. Finally, we improve robustness with checkpoint averaging and task-arithmetic merging. We release model checkpoints under Apache 2.0, and publicly release the dataset and \textbf{LightOnOCR-bbox-bench} evaluation under their respective licenses.		None
PubMed-OCR: PMC Open Access OCR Annotations	2026-01-16	Show PubMed-OCR is an OCR-centric corpus of scientific articles derived from PubMed Central Open Access PDFs. Each page image is annotated with Google Cloud Vision and released in a compact JSON schema with word-, line-, and paragraph-level bounding boxes. The corpus spans 209.5K articles (1.5M pages; ~1.3B words) and supports layout-aware modeling, coordinate-grounded QA, and evaluation of OCR-dependent pipelines. We analyze corpus characteristics (e.g., journal coverage and detected layout features) and discuss limitations, including reliance on a single OCR engine and heuristic line reconstruction. We release the data and schema to facilitate downstream research and invite extensions.		None
Visual Merit or Linguistic Crutch? A Close Look at DeepSeek-OCR	2026-01-07	Show DeepSeek-OCR utilizes an optical 2D mapping approach to achieve high-ratio vision-text compression, claiming to decode text tokens exceeding ten times the input visual tokens. While this suggests a promising solution for the LLM long-context bottleneck, we investigate a critical question: "Visual merit or linguistic crutch - which drives DeepSeek-OCR's performance?" By employing sentence-level and word-level semantic corruption, we isolate the model's intrinsic OCR capabilities from its language priors. Results demonstrate that without linguistic support, DeepSeek-OCR's performance plummets from approximately 90% to 20%. Comparative benchmarking against 13 baseline models reveals that traditional pipeline OCR methods exhibit significantly higher robustness to such semantic perturbations than end-to-end methods. Furthermore, we find that lower visual token counts correlate with increased reliance on priors, exacerbating hallucination risks. Context stress testing also reveals a total model collapse around 10,000 text tokens, suggesting that current optical compression techniques may paradoxically aggravate the long-context bottleneck. This study empirically defines DeepSeek-OCR's capability boundaries and offers essential insights for future optimizations of the vision-text compression paradigm. We release all data, results and scripts used in this study at https://github.com/dududuck00/DeepSeekOCR.		Code Link
600k-ks-ocr: a large-scale synthetic dataset for optical character recognition in kashmiri script	2026-01-03	Show This technical report presents the 600K-KS-OCR Dataset, a large-scale synthetic corpus comprising approximately 602,000 word-level segmented images designed for training and evaluating optical character recognition systems targeting Kashmiri script. The dataset addresses a critical resource gap for Kashmiri, an endangered Dardic language utilizing a modified Perso-Arabic writing system spoken by approximately seven million people. Each image is rendered at 256x64 pixels with corresponding ground-truth transcriptions provided in multiple formats compatible with CRNN, TrOCR, and generalpurpose machine learning pipelines. The generation methodology incorporates three traditional Kashmiri typefaces, comprehensive data augmentation simulating real-world document degradation, and diverse background textures to enhance model robustness. The dataset is distributed across ten partitioned archives totaling approximately 10.6 GB and is released under the CC-BY-4.0 license to facilitate research in low-resource language optical character recognition.		None
Seeing Justice Clearly: Handwritten Legal Document Translation with OCR and Vision-Language Models	2025-12-19	Show Handwritten text recognition (HTR) and machine translation continue to pose significant challenges, particularly for low-resource languages like Marathi, which lack large digitized corpora and exhibit high variability in handwriting styles. The conventional approach to address this involves a two-stage pipeline: an OCR system extracts text from handwritten images, which is then translated into the target language using a machine translation model. In this work, we explore and compare the performance of traditional OCR-MT pipelines with Vision Large Language Models that aim to unify these stages and directly translate handwritten text images in a single, end-to-end step. Our motivation is grounded in the urgent need for scalable, accurate translation systems to digitize legal records such as FIRs, charge sheets, and witness statements in India's district and high courts. We evaluate both approaches on a curated dataset of handwritten Marathi legal documents, with the goal of enabling efficient legal document processing, even in low-resource environments. Our findings offer actionable insights toward building robust, edge-deployable solutions that enhance access to legal information for non-native speakers and legal professionals alike.	Accep... Accepted in AILaw @ AAAI 2026 Conference	None
Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR	2025-12-11	Show Reading text from images or scanned documents via OCR models has been a longstanding focus of researchers. Intuitively, text reading is perceived as a straightforward perceptual task, and existing work primarily focuses on constructing enriched data engineering to enhance SFT capabilities. In this work, we observe that even advanced OCR models exhibit significantly higher entropy in formatted text (\emph{e.g.}, formula, table, etc.) compared to plain text, often by an order of magnitude. These statistical patterns reveal that advanced OCR models struggle with high output uncertainty when dealing with format sensitive document, suggesting that reasoning over diverse reading pathways may improve OCR performance. To address this, we propose format decoupled reinforcement learning (FD-RL), which leverages high-entropy patterns for targeted optimization. Our approach employs entropy-based data filtration strategy to identify format-intensive instances, and adopt format decoupled rewards tailored to different format types, enabling format-level validation rather than token-level memorization. FD-RL achieves an average score of 90.41 on OmniDocBench, setting a new record for end-to-end models on this highly popular benchmark. More importantly, we conduct comprehensive ablation studies over data, training, filtering, and rewarding strategies, thoroughly validating their effectiveness.	technical report	None
Reading Between the Lines: Abstaining from VLM-Generated OCR Errors via Latent Representation Probes	2025-11-25	Show As VLMs are deployed in safety-critical applications, their ability to abstain from answering when uncertain becomes crucial for reliability, especially in Scene Text Visual Question Answering (STVQA) tasks. For example, OCR errors like misreading "50 mph" as "60 mph" could cause severe traffic accidents. This leads us to ask: Can VLMs know when they can't see? Existing abstention methods suggest pessimistic answers: they either rely on miscalibrated output probabilities or require semantic agreement unsuitable for OCR tasks. However, this failure may indicate we are looking in the wrong place: uncertainty signals could be hidden in VLMs' internal representations. Building on this insight, we propose Latent Representation Probing (LRP): training lightweight probes on hidden states or attention patterns. We explore three probe designs: concatenating representations across all layers, aggregating attention over visual tokens, and ensembling single layer probes by majority vote. Experiments on four benchmarks across image and video modalities show LRP improves abstention accuracy by 7.6% over best baselines. Our analysis reveals: probes generalize across various uncertainty sources and datasets, and optimal signals emerge from intermediate rather than final layers. This establishes a principled framework for building deployment-ready AI systems by detecting confidence signals from internal states rather than unreliable outputs.		None
Vision Token Masking Alone Cannot Prevent PHI Leakage in Medical Document OCR: A Systematic Evaluation	2025-11-23	Show Large vision-language models (VLMs) are increasingly deployed for optical character recognition (OCR) in healthcare settings, raising critical concerns about protected health information (PHI) exposure during document processing. This work presents the first systematic evaluation of inference-time vision token masking as a privacy-preserving mechanism for medical document OCR using DeepSeek-OCR. We introduce seven masking strategies (V3-V9) targeting different architectural layers (SAM encoder blocks, compression layers, dual vision encoders, projector fusion) and evaluate PHI reduction across HIPAA-defined categories using 100 synthetic medical billing statements (drawn from a corpus of 38,517 annotated documents) with perfect ground-truth annotations. All masking strategies converge to 42.9% PHI reduction, successfully suppressing long-form spatially-distributed identifiers (patient names, dates of birth, physical addresses at 100% effectiveness) while failing to prevent short structured identifiers (medical record numbers, social security numbers, email addresses, account numbers at 0% effectiveness). Ablation studies varying mask expansion radius (r=1,2,3) demonstrate that increased spatial coverage does not improve reduction beyond this ceiling, indicating that language model contextual inference - not insufficient visual masking - drives structured identifier leakage. A simulated hybrid architecture combining vision masking with NLP post-processing achieves 88.6% total PHI reduction (assuming 80% NLP accuracy on remaining identifiers). This negative result establishes boundaries for vision-only privacy interventions in VLMs, provides guidance distinguishing PHI types amenable to vision-level versus language-level redaction, and redirects future research toward decoder-level fine-tuning and hybrid defense-in-depth architectures for HIPAA-compliant medical document processing.	24 pa... 24 pages, 11 figures, 2 tables	None
TopoReformer: Mitigating Adversarial Attacks Using Topological Purification in OCR Models	2025-11-19	Show Adversarially perturbed images of text can cause sophisticated OCR systems to produce misleading or incorrect transcriptions from seemingly invisible changes to humans. Some of these perturbations even survive physical capture, posing security risks to high-stakes applications such as document processing, license plate recognition, and automated compliance systems. Existing defenses, such as adversarial training, input preprocessing, or post-recognition correction, are often model-specific, computationally expensive, and affect performance on unperturbed inputs while remaining vulnerable to unseen or adaptive attacks. To address these challenges, TopoReformer is introduced, a model-agnostic reformation pipeline that mitigates adversarial perturbations while preserving the structural integrity of text images. Topology studies properties of shapes and spaces that remain unchanged under continuous deformations, focusing on global structures such as connectivity, holes, and loops rather than exact distance. Leveraging these topological features, TopoReformer employs a topological autoencoder to enforce manifold-level consistency in latent space and improve robustness without explicit gradient regularization. The proposed method is benchmarked on EMNIST, MNIST, against standard adversarial attacks (FGSM, PGD, Carlini-Wagner), adaptive attacks (EOT, BDPA), and an OCR-specific watermark attack (FAWA).	Accep... Accepted at AAAI 2026 AI for CyberSecurity (AICS) Workshop	None
FinCriticalED: A Visual Benchmark for Financial Fact-Level OCR Evaluation	2025-11-19	Show We introduce FinCriticalED (Financial Critical Error Detection), a visual benchmark for evaluating OCR and vision language models on financial documents at the fact level. Financial documents contain visually dense and table heavy layouts where numerical and temporal information is tightly coupled with structure. In high stakes settings, small OCR mistakes such as sign inversion or shifted dates can lead to materially different interpretations, while traditional OCR metrics like ROUGE and edit distance capture only surface level text similarity. \ficriticaled provides 500 image-HTML pairs with expert annotated financial facts covering over seven hundred numerical and temporal facts. It introduces three key contributions. First, it establishes the first fact level evaluation benchmark for financial document understanding, shifting evaluation from lexical overlap to domain critical factual correctness. Second, all annotations are created and verified by financial experts with strict quality control over signs, magnitudes, and temporal expressions. Third, we develop an LLM-as-Judge evaluation pipeline that performs structured fact extraction and contextual verification for visually complex financial documents. We benchmark OCR systems, open source vision language models, and proprietary models on FinCriticalED. Results show that although the strongest proprietary models achieve the highest factual accuracy, substantial errors remain in visually intricate numerical and temporal contexts. Through quantitative evaluation and expert case studies, FinCriticalED provides a rigorous foundation for advancing visual factual precision in financial and other precision critical domains.	Yueru... Yueru He, Xueqing Peng: These two authors contributed equally to this work	None
AnonLFI 2.0: Extensible Architecture for PII Pseudonymization in CSIRTs with OCR and Technical Recognizers	2025-11-18	Show This work presents AnonLFI 2.0, a modular pseudonymization framework for CSIRTs that uses HMAC SHA256 to generate strong and reversible pseudonyms, preserves XML and JSON structures, and integrates OCR and technical recognizers for PII and security artifacts. In two case studies involving OCR applied to PDF documents and an OpenVAS XML report, the system achieved perfect precision and F1 scores of 76.5 and 92.13, demonstrating its effectiveness for securely preparing complex cybersecurity datasets.	4 pag... 4 pages, 1 figure, 2 tabels, submitted to ERRC/WRSeg 2025	None
Enriching Historical Records: An OCR and AI-Driven Approach for Database Integration	2025-11-17	Show This research digitizes and analyzes the Leidse hoogleraren en lectoren 1575-1815 books written between 1983 and 1985, which contain biographic data about professors and curators of Leiden University. It addresses the central question: how can we design an automated pipeline that integrates OCR, LLM-based interpretation, and database linking to harmonize data from historical document images with existing high-quality database records? We applied OCR techniques, generative AI decoding constraints that structure data extraction, and database linkage methods to process typewritten historical records into a digital format. OCR achieved a Character Error Rate (CER) of 1.08 percent and a Word Error Rate (WER) of 5.06 percent, while JSON extraction from OCR text achieved an average accuracy of 63 percent and, based on annotated OCR, 65 percent. This indicates that generative AI somewhat corrects low OCR performance. Our record linkage algorithm linked annotated JSON files with 94% accuracy and OCR-derived JSON files with 81%. This study contributes to digital humanities research by offering an automated pipeline for interpreting digitized historical documents, addressing challenges like layout variability and terminology differences, and exploring the applicability and strength of an advanced generative AI model.		None
Compact Multimodal Language Models as Robust OCR Alternatives for Noisy Textual Clinical Reports	2025-11-17	Show Digitization of medical records often relies on smartphone photographs of printed reports, producing images degraded by blur, shadows, and other noise. Conventional OCR systems, optimized for clean scans, perform poorly under such real-world conditions. This study evaluates compact multimodal language models as privacy-preserving alternatives for transcribing noisy clinical documents. Using obstetric ultrasound reports written in regionally inflected medical English common to Indian healthcare settings, we compare eight systems in terms of transcription accuracy, noise sensitivity, numeric accuracy, and computational efficiency. Compact multimodal models consistently outperform both classical and neural OCR pipelines. Despite higher computational costs, their robustness and linguistic adaptability position them as viable candidates for on-premises healthcare digitization.		None
Automated Invoice Data Extraction: Using LLM and OCR	2025-11-11	Show Conventional Optical Character Recognition (OCR) systems are challenged by variant invoice layouts, handwritten text, and low- quality scans, which are often caused by strong template dependencies that restrict their flexibility across different document structures and layouts. Newer solutions utilize advanced deep learning models such as Convolutional Neural Networks (CNN) as well as Transformers, and domain-specific models for better layout analysis and accuracy across various sections over varied document types. Large Language Models (LLMs) have revolutionized extraction pipelines at their core with sophisticated entity recognition and semantic comprehension to support complex contextual relationship mapping without direct programming specification. Visual Named Entity Recognition (NER) capabilities permit extraction from invoice images with greater contextual sensitivity and much higher accuracy rates than older approaches. Existing industry best practices utilize hybrid architectures that blend OCR technology and LLM for maximum scalability and minimal human intervention. This work introduces a holistic Artificial Intelligence (AI) platform combining OCR, deep learning, LLMs, and graph analytics to achieve unprecedented extraction quality and consistency.	10 pages, 3 figures	None
Seeing Straight: Document Orientation Detection for Efficient OCR	2025-11-06	Show Despite significant advances in document understanding, determining the correct orientation of scanned or photographed documents remains a critical pre-processing step in the real world settings. Accurate rotation correction is essential for enhancing the performance of downstream tasks such as Optical Character Recognition (OCR) where misalignment commonly arises due to user errors, particularly incorrect base orientations of the camera during capture. In this study, we first introduce OCR-Rotation-Bench (ORB), a new benchmark for evaluating OCR robustness to image rotations, comprising (i) ORB-En, built from rotation-transformed structured and free-form English OCR datasets, and (ii) ORB-Indic, a novel multilingual set spanning 11 Indic mid to low-resource languages. We also present a fast, robust and lightweight rotation classification pipeline built on the vision encoder of Phi-3.5-Vision model with dynamic image cropping, fine-tuned specifically for 4-class rotation task in a standalone fashion. Our method achieves near-perfect 96% and 92% accuracy on identifying the rotations respectively on both the datasets. Beyond classification, we demonstrate the critical role of our module in boosting OCR performance: closed-source (up to 14%) and open-weights models (up to 4x) in the simulated real-world setting.		None
Cross-Lingual SynthDocs: A Large-Scale Synthetic Corpus for Any to Arabic OCR and Document Understanding	2025-11-01	Show Cross-Lingual SynthDocs is a large-scale synthetic corpus designed to address the scarcity of Arabic resources for Optical Character Recognition (OCR) and Document Understanding (DU). The dataset comprises over 2.5 million of samples, including 1.5 million textual data, 270K fully annotated tables, and hundred thousands of real data based charts. Our pipeline leverages authentic scanned backgrounds, bilingual layouts, and diacritic aware fonts to capture the typographic and structural complexity of Arabic documents. In addition to text, the corpus includes variety of rendered styles for charts and tables. Finetuning Qwen-2.5-VL on SynthDocs yields consistent improvements in Word Error Rate (WER) and Character Error Rate (CER) in terms of OCR across multiple public Arabic benchmarks, Tree-Edit Distance Similarity (TEDS) and Chart Extraction Score (CharTeX) improved as well in other modalities. SynthDocs provides a scalable, visually realistic resource for advancing research in multilingual document analysis.		None
Multi-Stage Field Extraction of Financial Documents with OCR and Compact Vision-Language Models	2025-10-27	Show Financial documents are essential sources of information for regulators, auditors, and financial institutions, particularly for assessing the wealth and compliance of Small and Medium-sized Businesses. However, SMB documents are often difficult to parse. They are rarely born digital and instead are distributed as scanned images that are none machine readable. The scans themselves are low in resolution, affected by skew or rotation, and often contain noisy backgrounds. These documents also tend to be heterogeneous, mixing narratives, tables, figures, and multilingual content within the same report. Such characteristics pose major challenges for automated information extraction, especially when relying on end to end large Vision Language Models, which are computationally expensive, sensitive to noise, and slow when applied to files with hundreds of pages. We propose a multistage pipeline that leverages traditional image processing models and OCR extraction, together with compact VLMs for structured field extraction of large-scale financial documents. Our approach begins with image pre-processing, including segmentation, orientation detection, and size normalization. Multilingual OCR is then applied to recover page-level text. Upon analyzing the text information, pages are retrieved for coherent sections. Finally, compact VLMs are operated within these narrowed-down scopes to extract structured financial indicators. Our approach is evaluated using an internal corpus of multi-lingual, scanned financial documents. The results demonstrate that compact VLMs, together with a multistage pipeline, achieves 8.8 times higher field level accuracy relative to directly feeding the whole document into large VLMs, only at 0.7 percent of the GPU cost and 92.6 percent less end-to-end service latency.		None
DeepSeek-OCR: Contexts Optical Compression	2025-10-22	Show We present DeepSeek-OCR as an initial investigation into the feasibility of compressing long contexts via optical 2D mapping. DeepSeek-OCR consists of two components: DeepEncoder and DeepSeek3B-MoE-A570M as the decoder. Specifically, DeepEncoder serves as the core engine, designed to maintain low activations under high-resolution input while achieving high compression ratios to ensure an optimal and manageable number of vision tokens. Experiments show that when the number of text tokens is within 10 times that of vision tokens (i.e., a compression ratio < 10x), the model can achieve decoding (OCR) precision of 97%. Even at a compression ratio of 20x, the OCR accuracy still remains at about 60%. This shows considerable promise for research areas such as historical long-context compression and memory forgetting mechanisms in LLMs. Beyond this, DeepSeek-OCR also demonstrates high practical value. On OmniDocBench, it surpasses GOT-OCR2.0 (256 tokens/page) using only 100 vision tokens, and outperforms MinerU2.0 (6000+ tokens per page on average) while utilizing fewer than 800 vision tokens. In production, DeepSeek-OCR can generate training data for LLMs/VLMs at a scale of 200k+ pages per day (a single A100-40G). Codes and model weights are publicly accessible at http://github.com/deepseek-ai/DeepSeek-OCR.		Code Link
olmOCR 2: Unit Test Rewards for Document OCR	2025-10-22	Show We present olmOCR 2, the latest in our family of powerful OCR systems for converting digitized print documents, like PDFs, into clean, naturally ordered plain text. olmOCR 2 is powered by olmOCR-2-7B-1025, a specialized, 7B vision language model (VLM) trained using reinforcement learning with verifiable rewards (RLVR), where our rewards are a diverse set of binary unit tests. To scale unit test creation, we develop a pipeline for generating synthetic documents with diverse and challenging layouts, known ground-truth HTML source code, and extracted test cases. We show that RL training on these test cases results in state-of-the-art performance on olmOCR-Bench, our English-language OCR benchmark, with the largest improvements in math formula conversion, table parsing, and multi-column layouts compared to previous versions. We release our model, data and code under permissive open licenses.	https... https://olmocr.allen.ai/	None
OCR-APT: Reconstructing APT Stories from Audit Logs using Subgraph Anomaly Detection and LLMs	2025-10-21	Show Advanced Persistent Threats (APTs) are stealthy cyberattacks that often evade detection in system-level audit logs. Provenance graphs model these logs as connected entities and events, revealing relationships that are missed by linear log representations. Existing systems apply anomaly detection to these graphs but often suffer from high false positive rates and coarse-grained alerts. Their reliance on node attributes like file paths or IPs leads to spurious correlations, reducing detection robustness and reliability. To fully understand an attack's progression and impact, security analysts need systems that can generate accurate, human-like narratives of the entire attack. To address these challenges, we introduce OCR-APT, a system for APT detection and reconstruction of human-like attack stories. OCR-APT uses Graph Neural Networks (GNNs) for subgraph anomaly detection, learning behavior patterns around nodes rather than fragile attributes such as file paths or IPs. This approach leads to a more robust anomaly detection. It then iterates over detected subgraphs using Large Language Models (LLMs) to reconstruct multi-stage attack stories. Each stage is validated before proceeding, reducing hallucinations and ensuring an interpretable final report. Our evaluations on the DARPA TC3, OpTC, and NODLINK datasets show that OCR-APT outperforms state-of-the-art systems in both detection accuracy and alert interpretability. Moreover, OCR-APT reconstructs human-like reports that comprehensively capture the attack story.	This ... This is the authors' extended version of the paper accepted for publication at the ACM SIGSAC Conference on Computer and Communications Security (CCS 2025). The final published version is available at https://doi.org/10.1145/3719027.3765219	None
Automated Wicket-Taking Delivery Segmentation and Weakness Detection in Cricket Videos Using OCR-Guided YOLOv8 and Trajectory Modeling	2025-10-21	Show This paper presents an automated system for cricket video analysis that leverages deep learning techniques to extract wicket-taking deliveries, detect cricket balls, and model ball trajectories. The system employs the YOLOv8 architecture for pitch and ball detection, combined with optical character recognition (OCR) for scorecard extraction to identify wicket-taking moments. Through comprehensive image preprocessing, including grayscale transformation, power transformation, and morphological operations, the system achieves robust text extraction from video frames. The pitch detection model achieved 99.5% mean Average Precision at 50% IoU (mAP50) with a precision of 0.999, while the ball detection model using transfer learning attained 99.18% mAP50 with 0.968 precision and 0.978 recall. The system enables trajectory modeling on detected pitches, providing data-driven insights for identifying batting weaknesses. Experimental results on multiple cricket match videos demonstrate the effectiveness of this approach for automated cricket analytics, offering significant potential for coaching and strategic decision-making.	6 fig... 6 figures, 5 tables, submitted to the 11th IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering 2025	None
OCR-Quality: A Human-Annotated Dataset for OCR Quality Assessment	2025-10-17	Show We present OCR-Quality, a comprehensive human-annotated dataset designed for evaluating and developing OCR quality assessment methods. The dataset consists of 1,000 PDF pages converted to PNG images at 300 DPI, sampled from diverse real-world scenarios, including academic papers, textbooks, e-books, and multilingual documents. Each document has been processed using state-of-the-art Vision-Language Models (VLMs) and manually annotated with quality scores using a 4-level scoring system (1: Excellent, 2: Good, 3: Fair, 4: Poor). The dataset includes detailed source information, annotation guidelines, and representative cases across various difficulty levels. OCR-Quality addresses the critical need for reliable OCR quality assessment in real-world applications and provides a valuable benchmark for training and evaluating OCR verification systems. The dataset is publicly available at https://huggingface.co/datasets/Aslan-mingye/OCR-Quality .		None
VOLTAGE: A Versatile Contrastive Learning based OCR Methodology for ultra low-resource scripts through Auto Glyph Feature Extraction	2025-10-12	Show UNESCO has classified 2500 out of 7000 languages spoken worldwide as endangered. Attrition of a language leads to loss of traditional wisdom, folk literature, and the essence of the community that uses it. It is therefore imperative to bring digital inclusion to these languages and avoid its extinction. Low resource languages are at a greater risk of extinction. Lack of unsupervised Optical Character Recognition(OCR) methodologies for low resource languages is one of the reasons impeding their digital inclusion. We propose VOLTAGE - a contrastive learning based OCR methodology, leveraging auto-glyph feature recommendation for cluster-based labelling. We augment the labelled data for diversity and volume using image transformations and Generative Adversarial Networks. Voltage has been designed using Takri - a family of scripts used in 16th to 20th century in the Himalayan regions of India. We present results for Takri along with other Indic scripts (both low and high resource) to substantiate the universal behavior of the methodology. An accuracy of 95% for machine printed and 87% for handwritten samples on Takri script has been achieved. We conduct baseline and ablation studies along with building downstream use cases for Takri, demonstrating the usefulness of our work.	9 Pag... 9 Pages, Plus Appendices, EACL 2024	None
Hybrid OCR-LLM Framework for Enterprise-Scale Document Information Extraction Under Copy-heavy Task	2025-10-11	Show Information extraction from copy-heavy documents, characterized by massive volumes of structurally similar content, represents a critical yet understudied challenge in enterprise document processing. We present a systematic framework that strategically combines OCR engines with Large Language Models (LLMs) to optimize the accuracy-efficiency trade-off inherent in repetitive document extraction tasks. Unlike existing approaches that pursue universal solutions, our method exploits document-specific characteristics through intelligent strategy selection. We implement and evaluate 25 configurations across three extraction paradigms (direct, replacement, and table-based) on identity documents spanning four formats (PNG, DOCX, XLSX, PDF). Through table-based extraction methods, our adaptive framework delivers outstanding results: F1=1.0 accuracy with 0.97s latency for structured documents, and F1=0.997 accuracy with 0.6 s for challenging image inputs when integrated with PaddleOCR, all while maintaining sub-second processing speeds. The 54 times performance improvement compared with multimodal methods over naive approaches, coupled with format-aware routing, enables processing of heterogeneous document streams at production scale. Beyond the specific application to identity extraction, this work establishes a general principle: the repetitive nature of copy-heavy tasks can be transformed from a computational burden into an optimization opportunity through structure-aware method selection.		None
When Vision Fails: Text Attacks Against ViT and OCR	2025-10-11	Show Text-based machine learning models are vulnerable to an emerging class of Unicode-based adversarial examples capable of tricking a model into misreading text with potentially disastrous effects. The primary existing defense against these attacks is to preprocess potentially malicious text inputs using optical character recognition (OCR). In theory, OCR models will ignore any malicious Unicode characters and will extract the visually correct input to be fed to the model. In this work, we show that these visual defenses fail to prevent this type of attack. We use a genetic algorithm to generate visual adversarial examples (i.e., OCR outputs) in a black-box setting, demonstrating a highly effective novel attack that substantially reduces the accuracy of OCR and other visual models. Specifically, we use the Unicode functionality of combining characters (e.g., ~n which combines the characters n and ~) to manipulate text inputs so that small visual perturbations appear when the text is displayed. We demonstrate the effectiveness of these attacks in the real world by creating adversarial examples against production models published by Meta, Microsoft, IBM, and Google. We additionally conduct a user study to establish that the model-fooling adversarial examples do not affect human comprehension of the text, showing that language models are uniquely vulnerable to this type of text attack.	To ap... To appear in the 2nd ACM Workshop on Large AI Systems and Models with Privacy and Security Analysis	None
Evaluating LLMs for Historical Document OCR: A Methodological Framework for Digital Humanities	2025-10-08	Show Digital humanities scholars increasingly use Large Language Models for historical document digitization, yet lack appropriate evaluation frameworks for LLM-based OCR. Traditional metrics fail to capture temporal biases and period-specific errors crucial for historical corpus creation. We present an evaluation methodology for LLM-based historical OCR, addressing contamination risks and systematic biases in diplomatic transcription. Using 18th-century Russian Civil font texts, we introduce novel metrics including Historical Character Preservation Rate (HCPR) and Archaic Insertion Rate (AIR), alongside protocols for contamination control and stability testing. We evaluate 12 multimodal LLMs, finding that Gemini and Qwen models outperform traditional OCR while exhibiting over-historicization: inserting archaic characters from incorrect historical periods. Post-OCR correction degrades rather than improves performance. Our methodology provides digital humanities practitioners with guidelines for model selection and quality assessment in historical corpus digitization.	The F... The First Workshop on Natural Language Processing and Language Models for Digital Humanities (LM4DH 2025). RANLP 2025	None
Enhancing OCR for Sino-Vietnamese Language Processing via Fine-tuned PaddleOCRv5	2025-10-05	Show Recognizing and processing Classical Chinese (Han-Nom) texts play a vital role in digitizing Vietnamese historical documents and enabling cross-lingual semantic research. However, existing OCR systems struggle with degraded scans, non-standard glyphs, and handwriting variations common in ancient sources. In this work, we propose a fine-tuning approach for PaddleOCRv5 to improve character recognition on Han-Nom texts. We retrain the text recognition module using a curated subset of ancient Vietnamese Chinese manuscripts, supported by a full training pipeline covering preprocessing, LMDB conversion, evaluation, and visualization. Experimental results show a significant improvement over the base model, with exact accuracy increasing from 37.5 percent to 50.0 percent, particularly under noisy image conditions. Furthermore, we develop an interactive demo that visually compares pre- and post-fine-tuning recognition results, facilitating downstream applications such as Han-Vietnamese semantic alignment, machine translation, and historical linguistics research. The demo is available at https://huggingface.co/spaces/MinhDS/Fine-tuned-PaddleOCRv5.	5 pag... 5 pages, 6 figures, 2 tables	None
Evaluating OCR performance on food packaging labels in South Africa	2025-10-03	Show This study evaluates four open-source Optical Character Recognition (OCR) systems which are Tesseract, EasyOCR, PaddleOCR, and TrOCR on real world food packaging images. The aim is to assess their ability to extract ingredient lists and nutrition facts panels. Accurate OCR for packaging is important for compliance and nutrition monitoring but is challenging due to multilingual text, dense layouts, varied fonts, glare, and curved surfaces. A dataset of 231 products (1,628 images) was processed by all four models to assess speed and coverage, and a ground truth subset of 113 images (60 products) was created for accuracy evaluation. Metrics include Character Error Rate (CER), Word Error Rate (WER), BLEU, ROUGE-L, F1, coverage, and execution time. On the ground truth subset, Tesseract achieved the lowest CER (0.912) and the highest BLEU (0.245). EasyOCR provided a good balance between accuracy and multilingual support. PaddleOCR achieved near complete coverage but was slower because it ran on CPU only due to GPU incompatibility, and TrOCR produced the weakest results despite GPU acceleration. These results provide a packaging-specific benchmark, establish a baseline, and highlight directions for layout-aware methods and text localization.	17 pages	None
Exploring OCR-augmented Generation for Bilingual VQA	2025-10-02	Show We investigate OCR-augmented generation with Vision Language Models (VLMs), exploring tasks in Korean and English toward multilingualism. To support research in this domain, we train and release KLOCR, a strong bilingual OCR baseline trained on 100M instances to augment VLMs with OCR ability. To complement existing VQA benchmarks, we curate KOCRBench for Korean VQA, and analyze different prompting methods. Extensive experiments show that OCR-extracted text significantly boosts performance across open source and commercial models. Our work offers new insights into OCR-augmented generation for bilingual VQA. Model, code, and data are available at https://github.com/JHLee0513/KLOCR.		Code Link
Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR	2025-09-17	Show Arabic document OCR remains a challenging task due to the language's cursive script, diverse fonts, diacritics, and right-to-left orientation. While modern Multimodal Large Language Models (MLLMs) have advanced document understanding for high-resource languages, their performance on Arabic remains limited. In this work, we introduce Baseer, a vision-language model fine- tuned specifically for Arabic document OCR. Leveraging a large-scale dataset combining synthetic and real-world documents, Baseer is trained using a decoder-only fine-tuning strategy to adapt a pre-trained MLLM while preserving general visual features. We also present Misraj-DocOCR, a high-quality, expert-verified benchmark designed for rigorous evaluation of Arabic OCR systems. Our experiments show that Baseer significantly outperforms existing open-source and commercial solutions, achieving a WER of 0.25 and establishing a new state-of-the-art in the domain of Arabic document OCR. Our results highlight the benefits of domain-specific adaptation of general-purpose MLLMs and establish a strong baseline for high-accuracy OCR on morphologically rich languages like Arabic.		None
Layout-Aware OCR for Black Digital Archives with Unsupervised Evaluation	2025-09-16	Show Despite their cultural and historical significance, Black digital archives continue to be a structurally underrepresented area in AI research and infrastructure. This is especially evident in efforts to digitize historical Black newspapers, where inconsistent typography, visual degradation, and limited annotated layout data hinder accurate transcription, despite the availability of various systems that claim to handle optical character recognition (OCR) well. In this short paper, we present a layout-aware OCR pipeline tailored for Black newspaper archives and introduce an unsupervised evaluation framework suited to low-resource archival contexts. Our approach integrates synthetic layout generation, model pretraining on augmented data, and a fusion of state-of-the-art You Only Look Once (YOLO) detectors. We used three annotation-free evaluation metrics, the Semantic Coherence Score (SCS), Region Entropy (RE), and Textual Redundancy Score (TRS), which quantify linguistic fluency, informational diversity, and redundancy across OCR regions. Our evaluation on a 400-page dataset from ten Black newspaper titles demonstrates that layout-aware OCR improves structural diversity and reduces redundancy compared to full-page baselines, with modest trade-offs in coherence. Our results highlight the importance of respecting cultural layout logic in AI-driven document understanding and lay the foundation for future community-driven and ethically grounded archival AI systems.	IEEE-... IEEE-ISTAS conference	None
Evaluation of Ensemble Learning Techniques for handwritten OCR Improvement	2025-09-11	Show For the bachelor project 2021 of Professor Lippert's research group, handwritten entries of historical patient records needed to be digitized using Optical Character Recognition (OCR) methods. Since the data will be used in the future, a high degree of accuracy is naturally required. Especially in the medical field this has even more importance. Ensemble Learning is a method that combines several machine learning models and is claimed to be able to achieve an increased accuracy for existing methods. For this reason, Ensemble Learning in combination with OCR is investigated in this work in order to create added value for the digitization of the patient records. It was possible to discover that ensemble learning can lead to an increased accuracy for OCR, which methods were able to achieve this and that the size of the training data set did not play a role here.		None
Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning	2025-09-10	Show Chinese ancient documents, invaluable carriers of millennia of Chinese history and culture, hold rich knowledge across diverse fields but face challenges in digitization and understanding, i.e., traditional methods only scan images, while current Vision-Language Models (VLMs) struggle with their visual and linguistic complexity. Existing document benchmarks focus on English printed texts or simplified Chinese, leaving a gap for evaluating VLMs on ancient Chinese documents. To address this, we present AncientDoc, the first benchmark for Chinese ancient documents, designed to assess VLMs from OCR to knowledge reasoning. AncientDoc includes five tasks (page-level OCR, vernacular translation, reasoning-based QA, knowledge-based QA, linguistic variant QA) and covers 14 document types, over 100 books, and about 3,000 pages. Based on AncientDoc, we evaluate mainstream VLMs using multiple metrics, supplemented by a human-aligned large language model for scoring.		None
ReceiptSense: Beyond Traditional OCR -- A Dataset for Receipt Understanding	2025-09-10	Show Multilingual OCR and information extraction from receipts remains challenging, particularly for complex scripts like Arabic. We introduce \dataset, a comprehensive dataset designed for Arabic-English receipt understanding comprising 20,000 annotated receipts from diverse retail settings, 30,000 OCR-annotated images, and 10,000 item-level annotations, and a new Receipt QA subset with 1265 receipt images paired with 40 question-answer pairs each to support LLM evaluation for receipt understanding. The dataset captures merchant names, item descriptions, prices, receipt numbers, and dates to support object detection, OCR, and information extraction tasks. We establish baseline performance using traditional methods (Tesseract OCR) and advanced neural networks, demonstrating the dataset's effectiveness for processing complex, noisy real-world receipt layouts. Our publicly accessible dataset advances automated multilingual document processing research (see https://github.com/Update-For-Integrated-Business-AI/CORU ).		Code Link
Integrating Generative AI into Cybersecurity Education: A Study of OCR and Multimodal LLM-assisted Instruction	2025-09-03	Show This full paper describes an LLM-assisted instruction integrated with a virtual cybersecurity lab platform. The digital transformation of Fourth Industrial Revolution (4IR) systems is reshaping workforce needs, widening skill gaps, especially among older workers. With rising emphasis on robotics, automation, AI, and security, re-skilling and up-skilling are essential. Generative AI can help build this workforce by acting as an instructional assistant to support skill acquisition during experiential learning. We present a generative AI instructional assistant integrated into a prior experiential learning platform. The assistant employs a zero-shot OCR-LLM pipeline within the legacy Cybersecurity Labs-as-a-Service (CLaaS) platform (2015). Text is extracted from slide images using Tesseract OCR, then simplified instructions are generated via a general-purpose LLM, enabling real-time instructional support with minimal infrastructure. The system was evaluated in a live university course where student feedback (n=42) averaged 7.83/10, indicating strong perceived usefulness. A comparative study with multimodal LLMs that directly interpret slide images showed higher performance on visually dense slides, but the OCR-LLM pipeline provided comparable pedagogical value on text-centric slides with much lower computational overhead and cost. This work demonstrates that a lightweight, easily integrable pipeline can effectively extend legacy platforms with modern generative AI, offering scalable enhancements for student comprehension in technical education.	9 pag... 9 pages, 3 figures, accepted by IEEE FIE 2025	None
Why Stop at Words? Unveiling the Bigger Picture through Line-Level OCR	2025-08-29	Show Conventional optical character recognition (OCR) techniques segmented each character and then recognized. This made them prone to error in character segmentation, and devoid of context to exploit language models. Advances in sequence to sequence translation in last decade led to modern techniques first detecting words and then inputting one word at a time to a model to directly output full words as sequence of characters. This allowed better utilization of language models and bypass error-prone character segmentation step. We observe that the above transition in style has moved the bottleneck in accuracy to word segmentation. Hence, in this paper, we propose a natural and logical progression from word level OCR to line-level OCR. The proposal allows to bypass errors in word detection, and provides larger sentence context for better utilization of language models. We show that the proposed technique not only improves the accuracy but also efficiency of OCR. Despite our thorough literature survey, we did not find any public dataset to train and benchmark such shift from word to line-level OCR. Hence, we also contribute a meticulously curated dataset of 251 English page images with line-level annotations. Our experimentation revealed a notable end-to-end accuracy improvement of 5.4%, underscoring the potential benefits of transitioning towards line-level OCR, especially for document images. We also report a 4 times improvement in efficiency compared to word-based pipelines. With continuous improvements in large language models, our methodology also holds potential to exploit such advances. Project Website: https://nishitanand.github.io/line-level-ocr-website	11 pa... 11 pages. Project Website: https://nishitanand.github.io/line-level-ocr-website	Code Link
Improving OCR using internal document redundancy	2025-08-20	Show Current OCR systems are based on deep learning models trained on large amounts of data. Although they have shown some ability to generalize to unseen data, especially in detection tasks, they can struggle with recognizing low-quality data. This is particularly evident for printed documents, where intra-domain data variability is typically low, but inter-domain data variability is high. In that context, current OCR methods do not fully exploit each document's redundancy. We propose an unsupervised method by leveraging the redundancy of character shapes within a document to correct imperfect outputs of a given OCR system and suggest better clustering. To this aim, we introduce an extended Gaussian Mixture Model (GMM) by alternating an Expectation-Maximization (EM) algorithm with an intra-cluster realignment process and normality statistical testing. We demonstrate improvements in documents with various levels of degradation, including recovered Uruguayan military archives and 17th to mid-20th century European newspapers.	28 pa... 28 pages, 10 figures, including supplementary material. Code: https://github.com/seginusmowlavi/ocr-using-shape-redundancy. Dataset: https://github.com/camilomarino/ocr_berrutti_dataset	Code Link
DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Model	2025-08-18	Show Recent advances in large vision-language models (LVLMs) have enabled a new paradigm of end-to-end document image parsing, excelling in Optical Character Recognition (OCR) tasks such as text, table, and formula recognition. However, generative LVLMs, similarly to large language models (LLMs), are prone to hallucinations--generating words that do not exist in input images. Furthermore, LVLMs are designed for general purposes and tend to be less effective on OCR tasks compared to expert models that are trained on domain-specific datasets. In this paper, we propose DianJin-OCR-R1, a reasoning-enhanced framework designed to address these limitations through training reasoning-and-tool interleaved VLMs. Given a recognition instruction, our DianJin-OCR-R1 model first recognizes the content in the input image by its own OCR capabilities, and then calls other tools (i.e., other expert models) to obtain their results as references, finally looks again the image and rethinks about the reasoning process to provide the final recognized content. Since architectures of expert models are tailored for specific OCR tasks, which makes them less prone to hallucinations, their results can help VLMs mitigate hallucinations. Additionally, expert models are typically smaller in scale and easy to iterate, enabling performance improvements for VLMs at a lower cost. We evaluate our model on ReST and OmniDocBench, and experimental results show that our DianJin-OCR-R1 models consistently outperform their non-reasoning counterparts and expert OCR models, which proves the effectiveness of our method.		None
Improving OCR for Historical Texts of Multiple Languages	2025-08-14	Show This paper presents our methodology and findings from three tasks across Optical Character Recognition (OCR) and Document Layout Analysis using advanced deep learning techniques. First, for the historical Hebrew fragments of the Dead Sea Scrolls, we enhanced our dataset through extensive data augmentation and employed the Kraken and TrOCR models to improve character recognition. In our analysis of 16th to 18th-century meeting resolutions task, we utilized a Convolutional Recurrent Neural Network (CRNN) that integrated DeepLabV3+ for semantic segmentation with a Bidirectional LSTM, incorporating confidence-based pseudolabeling to refine our model. Finally, for modern English handwriting recognition task, we applied a CRNN with a ResNet34 encoder, trained using the Connectionist Temporal Classification (CTC) loss function to effectively capture sequential dependencies. This report offers valuable insights and suggests potential directions for future research.		None
Training Kindai OCR with parallel textline images and self-attention feature distance-based loss	2025-08-12	Show Kindai documents, written in modern Japanese from the late 19th to early 20th century, hold significant historical value for researchers studying societal structures, daily life, and environmental conditions of that period. However, transcribing these documents remains a labor-intensive and time-consuming task, resulting in limited annotated data for training optical character recognition (OCR) systems. This research addresses this challenge of data scarcity by leveraging parallel textline images - pairs of original Kindai text and their counterparts in contemporary Japanese fonts - to augment training datasets. We introduce a distance-based objective function that minimizes the gap between self-attention features of the parallel image pairs. Specifically, we explore Euclidean distance and Maximum Mean Discrepancy (MMD) as domain adaptation metrics. Experimental results demonstrate that our method reduces the character error rate (CER) by 2.23% and 3.94% over a Transformer-based OCR baseline when using Euclidean distance and MMD, respectively. Furthermore, our approach improves the discriminative quality of self-attention representations, leading to more effective OCR performance for historical documents.		None
Evaluating Robustness of LLMs in Question Answering on Multilingual Noisy OCR Data	2025-08-06	Show Optical Character Recognition (OCR) plays a crucial role in digitizing historical and multilingual documents, yet OCR errors - imperfect extraction of text, including character insertion, deletion, and substitution can significantly impact downstream tasks like question-answering (QA). In this work, we conduct a comprehensive analysis of how OCR-induced noise affects the performance of Multilingual QA Systems. To support this analysis, we introduce a multilingual QA dataset MultiOCR-QA, comprising 50K question-answer pairs across three languages, English, French, and German. The dataset is curated from OCR-ed historical documents, which include different levels and types of OCR noise. We then evaluate how different state-of-the-art Large Language models (LLMs) perform under different error conditions, focusing on three major OCR error types. Our findings show that QA systems are highly prone to OCR-induced errors and perform poorly on noisy OCR text. By comparing model performance on clean versus noisy texts, we provide insights into the limitations of current approaches and emphasize the need for more noise-resilient QA systems in historical digitization contexts.	Accep... Accepted at CIKM 2025	None
Comparing OCR Pipelines for Folkloristic Text Digitization	2025-07-25	Show The digitization of historical folkloristic materials presents unique challenges due to diverse text layouts, varying print and handwriting styles, and linguistic variations. This study explores different optical character recognition (OCR) approaches for Slovene folkloristic and historical text digitization, integrating both traditional methods and large language models (LLMs) to improve text transcription accuracy while maintaining linguistic and structural integrity. We compare single-stage OCR techniques with multi-stage pipelines that incorporate machine learning-driven post-processing for text normalization and layout reconstruction. While LLM-enhanced methods show promise in refining recognition outputs and improving readability, they also introduce challenges related to unintended modifications, particularly in the preservation of dialectal expressions and historical structures. Our findings provide insights into selecting optimal digitization strategies for large-scale folklore archives and outline recommendations for developing robust OCR pipelines that balance automation with the need for textual authenticity in digital humanities research.		None
Zero-shot OCR Accuracy of Low-Resourced Languages: A Comparative Analysis on Sinhala and Tamil	2025-07-24	Show Solving the problem of Optical Character Recognition (OCR) on printed text for Latin and its derivative scripts can now be considered settled due to the volumes of research done on English and other High-Resourced Languages (HRL). However, for Low-Resourced Languages (LRL) that use unique scripts, it remains an open problem. This study presents a comparative analysis of the zero-shot performance of six distinct OCR engines on two LRLs: Sinhala and Tamil. The selected engines include both commercial and open-source systems, aiming to evaluate the strengths of each category. The Cloud Vision API, Surya, Document AI, and Tesseract were evaluated for both Sinhala and Tamil, while Subasa OCR and EasyOCR were examined for only one language due to their limitations. The performance of these systems was rigorously analysed using five measurement techniques to assess accuracy at both the character and word levels. According to the findings, Surya delivered the best performance for Sinhala across all metrics, with a WER of 2.61%. Conversely, Document AI excelled across all metrics for Tamil, highlighted by a very low CER of 0.78%. In addition to the above analysis, we also introduce a novel synthetic Tamil OCR benchmarking dataset.	10 pa... 10 pages, 4 figures, Accepted paper at Recent Advances in Natural Language Processing (RANLP) 2025	None
Aesthetics is Cheap, Show me the Text: An Empirical Evaluation of State-of-the-Art Generative Models for OCR	2025-07-20	Show Text image is a unique and crucial information medium that integrates visual aesthetics and linguistic semantics in modern e-society. Due to their subtlety and complexity, the generation of text images represents a challenging and evolving frontier in the image generation field. The recent surge of specialized image generators (\emph{e.g.}, Flux-series) and unified generative models (\emph{e.g.}, GPT-4o), which demonstrate exceptional fidelity, raises a natural question: can they master the intricacies of text image generation and editing? Motivated by this, we assess current state-of-the-art generative models' capabilities in terms of text image generation and editing. We incorporate various typical optical character recognition (OCR) tasks into our evaluation and broaden the concept of text-based generation tasks into OCR generative tasks. We select 33 representative tasks and categorize them into five categories: document, handwritten text, scene text, artistic text, and complex & layout-rich text. For comprehensive evaluation, we examine six models across both closed-source and open-source domains, using tailored, high-quality image inputs and prompts. Through this evaluation, we draw crucial observations and identify the weaknesses of current generative models for OCR tasks. We argue that photorealistic text image generation and editing should be internalized as foundational skills into general-domain generative models, rather than being delegated to specialized solutions, and we hope this empirical analysis can provide valuable insights for the community to achieve this goal. This evaluation is online and will be continuously updated at our GitHub repository.		None
Seeing the Signs: A Survey of Edge-Deployable OCR Models for Billboard Visibility Analysis	2025-07-15	Show Outdoor advertisements remain a critical medium for modern marketing, yet accurately verifying billboard text visibility under real-world conditions is still challenging. Traditional Optical Character Recognition (OCR) pipelines excel at cropped text recognition but often struggle with complex outdoor scenes, varying fonts, and weather-induced visual noise. Recently, multimodal Vision-Language Models (VLMs) have emerged as promising alternatives, offering end-to-end scene understanding with no explicit detection step. This work systematically benchmarks representative VLMs - including Qwen 2.5 VL 3B, InternVL3, and SmolVLM2 - against a compact CNN-based OCR baseline (PaddleOCRv4) across two public datasets (ICDAR 2015 and SVT), augmented with synthetic weather distortions to simulate realistic degradation. Our results reveal that while selected VLMs excel at holistic scene reasoning, lightweight CNN pipelines still achieve competitive accuracy for cropped text at a fraction of the computational cost-an important consideration for edge deployment. To foster future research, we release our weather-augmented benchmark and evaluation code publicly.		None
Improving MLLM's Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency	2025-07-11	Show Multimodal Large Language Models (MLLMs) have shown strong performance in document image tasks, especially Optical Character Recognition (OCR). However, they struggle with Document Image Machine Translation (DIMT), which requires handling both cross-modal and cross-lingual challenges. Previous efforts to enhance DIMT capability through Supervised Fine-Tuning (SFT) on the DIMT dataset often result in the forgetting of the model's existing monolingual abilities, such as OCR. To address these challenges, we introduce a novel fine-tuning paradigm, named Synchronously Self-Reviewing (SSR) its OCR proficiency, inspired by the concept "Bilingual Cognitive Advantage". Specifically, SSR prompts the model to generate OCR text before producing translation text, which allows the model to leverage its strong monolingual OCR ability while learning to translate text across languages. Comprehensive experiments demonstrate the proposed SSR learning helps mitigate catastrophic forgetting, improving the generalization ability of MLLMs on both OCR and DIMT tasks.	Accep... Accepted by ACL 2025 Findings	None
Design and Implementation of an OCR-Powered Pipeline for Table Extraction from Invoices	2025-07-09	Show This paper presents the design and development of an OCR-powered pipeline for efficient table extraction from invoices. The system leverages Tesseract OCR for text recognition and custom post-processing logic to detect, align, and extract structured tabular data from scanned invoice documents. Our approach includes dynamic preprocessing, table boundary detection, and row-column mapping, optimized for noisy and non-standard invoice formats. The resulting pipeline significantly improves data extraction accuracy and consistency, supporting real-world use cases such as automated financial workflows and digital archiving.	17 pa... 17 pages, 23 figures, submitted to arXiv in July 2025	None
Finetuning Vision-Language Models as OCR Systems for Low-Resource Languages: A Case Study of Manchu	2025-07-09	Show Manchu, a critically endangered language essential for understanding early modern Eastern Eurasian history, lacks effective OCR systems that can handle real-world historical documents. This study develops high-performing OCR systems by fine-tuning three open-source vision-language models (LLaMA-3.2-11B, Qwen2.5-VL-7B, Qwen2.5-VL-3B) on 60,000 synthetic Manchu word images using parameter-efficient training. LLaMA-3.2-11B achieved exceptional performance with 98.3% word accuracy and 0.0024 character error rate on synthetic data, while crucially maintaining 93.1% accuracy on real-world handwritten documents. Comparative evaluation reveals substantial advantages over traditional approaches: while a CRNN baseline achieved 99.8% synthetic accuracy, it suffered severe degradation to 72.5% on real documents. Our approach demonstrates effective synthetic-to-real domain transfer, providing a cost-effective solution deployable on accessible infrastructure. This work establishes a transferable framework for endangered language OCR that removes technical and financial barriers in digital humanities, enabling historians and linguists to process historical archives without specialized computing resources. Code and model weights are available at https://github.com/mic7ch1/ManchuAI-OCR.		Code Link
TextPixs: Glyph-Conditioned Diffusion with Character-Aware Attention and OCR-Guided Supervision	2025-07-08	Show The modern text-to-image diffusion models boom has opened a new era in digital content production as it has proven the previously unseen ability to produce photorealistic and stylistically diverse imagery based on the semantics of natural-language descriptions. However, the consistent disadvantage of these models is that they cannot generate readable, meaningful, and correctly spelled text in generated images, which significantly limits the use of practical purposes like advertising, learning, and creative design. This paper introduces a new framework, namely Glyph-Conditioned Diffusion with Character-Aware Attention (GCDA), using which a typical diffusion backbone is extended by three well-designed modules. To begin with, the model has a dual-stream text encoder that encodes both semantic contextual information and explicit glyph representations, resulting in a character-aware representation of the input text that is rich in nature. Second, an attention mechanism that is aware of the character is proposed with a new attention segregation loss that aims to limit the attention distribution of each character independently in order to avoid distortion artifacts. Lastly, GCDA has an OCR-in-the-loop fine-tuning phase, where a full text perceptual loss, directly optimises models to be legible and accurately spell. Large scale experiments to benchmark datasets, such as MARIO-10M and T2I-CompBench, reveal that GCDA sets a new state-of-the-art on all metrics, with better character based metrics on text rendering (Character Error Rate: 0.08 vs 0.21 for the previous best; Word Error Rate: 0.15 vs 0.25), human perception, and comparable image synthesis quality on high-fidelity (FID: 14.3).	30 pages	None
Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models	2025-06-25	Show Recent advancements in multimodal large language models have enhanced document understanding by integrating textual and visual information. However, existing models exhibit incompleteness within their paradigm in real-world scenarios, particularly under visual degradation. In such conditions, the current response paradigm often fails to adequately perceive visual degradation and ambiguity, leading to overreliance on linguistic priors or misaligned visual-textual reasoning. This difficulty in recognizing uncertainty frequently results in the generation of hallucinatory content, especially when a precise answer is not feasible. To better demonstrate and analyze this phenomenon and problem, we propose KIE-HVQA, the first benchmark dedicated to evaluating OCR hallucination in degraded document understanding. This dataset includes test samples spanning identity cards and invoices, with simulated real-world degradations for OCR reliability. This setup allows for evaluating models' capacity, under degraded input, to distinguish reliable visual information and answer accordingly, thereby highlighting the challenge of avoiding hallucination on uncertain data. To achieve vision-faithful reasoning and thereby avoid the aforementioned issues, we further introduce a GRPO-based framework featuring a novel reward mechanism. By incorporating a self-awareness of visual uncertainty and an analysis method that initiates refusal to answer to increase task difficulty within our supervised fine-tuning and reinforcement learning framework, we successfully mitigated hallucinations in ambiguous regions. Experiments on Qwen2.5-VL demonstrate that our 7B-parameter model achieves a 22% absolute improvement in hallucination-free accuracy over GPT-4o on KIE-HVQA and there is no significant performance drop in standard tasks, highlighting both effectiveness and robustness.		None
Robustness Evaluation of OCR-based Visual Document Understanding under Multi-Modal Adversarial Attacks	2025-06-19	Show Visual Document Understanding (VDU) systems have achieved strong performance in information extraction by integrating textual, layout, and visual signals. However, their robustness under realistic adversarial perturbations remains insufficiently explored. We introduce the first unified framework for generating and evaluating multi-modal adversarial attacks on OCR-based VDU models. Our method covers six gradient-based layout attack scenarios, incorporating manipulations of OCR bounding boxes, pixels, and texts across both word and line granularities, with constraints on layout perturbation budget (e.g., IoU >= 0.6) to preserve plausibility. Experimental results across four datasets (FUNSD, CORD, SROIE, DocVQA) and six model families demonstrate that line-level attacks and compound perturbations (BBox + Pixel + Text) yield the most severe performance degradation. Projected Gradient Descent (PGD)-based BBox perturbations outperform random-shift baselines in all investigated models. Ablation studies further validate the impact of layout budget, text modification, and adversarial transferability.	8 pag... 8 pages, 1 figure, under review at EMNLP 2025	None
Intelligent Automation for FDI Facilitation: Optimizing Tariff Exemption Processes with OCR And Large Language Models	2025-06-12	Show Tariff exemptions are fundamental to attracting Foreign Direct Investment (FDI) into the manufacturing sector, though the associated administrative processes present areas for optimization for both investing entities and the national tax authority. This paper proposes a conceptual framework to empower tax administration by leveraging a synergistic integration of Optical Character Recognition (OCR) and Large Language Model (LLM) technologies. The proposed system is designed to first utilize OCR for intelligent digitization, precisely extracting data from diverse application documents and key regulatory texts such as tariff orders. Subsequently, the LLM would enhance the capabilities of administrative officers by automating the critical and time-intensive task of verifying submitted HS Tariff Codes for machinery, equipment, and raw materials against official exemption lists. By enhancing the speed and precision of these initial assessments, this AI-driven approach systematically reduces potential for non-alignment and non-optimized exemption utilization, thereby streamlining the investment journey for FDI companies. For the national administration, the benefits include a significant boost in operational capacity, reduced administrative load, and a strengthened control environment, ultimately improving the ease of doing business and solidifying the nation's appeal as a premier destination for high-value manufacturing FDI.		None
Digitization of Document and Information Extraction using OCR	2025-06-11	Show Retrieving accurate details from documents is a crucial task, especially when handling a combination of scanned images and native digital formats. This document presents a combined framework for text extraction that merges Optical Character Recognition (OCR) techniques with Large Language Models (LLMs) to deliver structured outputs enriched by contextual understanding and confidence indicators. Scanned files are processed using OCR engines, while digital files are interpreted through layout-aware libraries. The extracted raw text is subsequently analyzed by an LLM to identify key-value pairs and resolve ambiguities. A comparative analysis of different OCR tools is presented to evaluate their effectiveness concerning accuracy, layout recognition, and processing speed. The approach demonstrates significant improvements over traditional rule-based and template-based methods, offering enhanced flexibility and semantic precision across different document categories		None
Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCR	2025-06-11	Show We propose "Generative Fusion Decoding" (GFD), a novel shallow fusion framework designed to integrate large language models (LLMs) into cross-modal text recognition systems for automatic speech recognition (ASR) and optical character recognition (OCR). We derive the necessary formulations to enable GFD to operate across mismatched token spaces of different models by calculating likelihood at the byte level, thereby enabling seamless fusion and synchronous progression during the decoding process. GFD is plug-and-play by design, making it readily compatible with various auto-regressive models without the need for any re-training. GFD proves effective for general ASR and OCR tasks through intermediate and frequent interactions with LLMs, surpassing cascaded methods in English and Mandarin benchmarks. In addition, GFD transfers in-context learning abilities of LLMs and allows for adaptive ASR in instruction-aware and long-context settings, yielding significant WER reductions of up to 17.7%.		None
QARI-OCR: High-Fidelity Arabic Text Recognition through Multimodal Large Language Model Adaptation	2025-06-04	Show The inherent complexities of Arabic script; its cursive nature, diacritical marks (tashkeel), and varied typography, pose persistent challenges for Optical Character Recognition (OCR). We present Qari-OCR, a series of vision-language models derived from Qwen2-VL-2B-Instruct, progressively optimized for Arabic through iterative fine-tuning on specialized synthetic datasets. Our leading model, QARI v0.2, establishes a new open-source state-of-the-art with a Word Error Rate (WER) of 0.160, Character Error Rate (CER) of 0.061, and BLEU score of 0.737 on diacritically-rich texts. Qari-OCR demonstrates superior handling of tashkeel, diverse fonts, and document layouts, alongside impressive performance on low-resolution images. Further explorations (QARI v0.3) showcase strong potential for structural document understanding and handwritten text. This work delivers a marked improvement in Arabic OCR accuracy and efficiency, with all models and datasets released to foster further research.		None
Predicting the Past: Estimating Historical Appraisals with OCR and Machine Learning	2025-05-30	Show Despite well-documented consequences of the U.S. government's 1930s housing policies on racial wealth disparities, scholars have struggled to quantify its precise financial effects due to the inaccessibility of historical property appraisal records. Many counties still store these records in physical formats, making large-scale quantitative analysis difficult. We present an approach scholars can use to digitize historical housing assessment data, applying it to build and release a dataset for one county. Starting from publicly available scanned documents, we manually annotated property cards for over 12,000 properties to train and validate our methods. We use OCR to label data for an additional 50,000 properties, based on our two-stage approach combining classical computer vision techniques with deep learning-based OCR. For cases where OCR cannot be applied, such as when scanned documents are not available, we show how a regression model based on building feature data can estimate the historical values, and test the generalizability of this model to other counties. With these cost-effective tools, scholars, community activists, and policy makers can better analyze and understand the historical impacts of redlining.	Accep... Accepted to COMPASS 2025	None
SARD: A Large-Scale Synthetic Arabic OCR Dataset for Book-Style Text Recognition	2025-05-30	Show Arabic Optical Character Recognition (OCR) is essential for converting vast amounts of Arabic print media into digital formats. However, training modern OCR models, especially powerful vision-language models, is hampered by the lack of large, diverse, and well-structured datasets that mimic real-world book layouts. Existing Arabic OCR datasets often focus on isolated words or lines or are limited in scale, typographic variety, or structural complexity found in books. To address this significant gap, we introduce SARD (Large-Scale Synthetic Arabic OCR Dataset). SARD is a massive, synthetically generated dataset specifically designed to simulate book-style documents. It comprises 843,622 document images containing 690 million words, rendered across ten distinct Arabic fonts to ensure broad typographic coverage. Unlike datasets derived from scanned documents, SARD is free from real-world noise and distortions, offering a clean and controlled environment for model training. Its synthetic nature provides unparalleled scalability and allows for precise control over layout and content variation. We detail the dataset's composition and generation process and provide benchmark results for several OCR models, including traditional and deep learning approaches, highlighting the challenges and opportunities presented by this dataset. SARD serves as a valuable resource for developing and evaluating robust OCR and vision-language models capable of processing diverse Arabic book-style texts.		None
TextSR: Diffusion Super-Resolution with Multilingual OCR Guidance	2025-05-29	Show While recent advancements in Image Super-Resolution (SR) using diffusion models have shown promise in improving overall image quality, their application to scene text images has revealed limitations. These models often struggle with accurate text region localization and fail to effectively model image and multilingual character-to-shape priors. This leads to inconsistencies, the generation of hallucinated textures, and a decrease in the perceived quality of the super-resolved text. To address these issues, we introduce TextSR, a multimodal diffusion model specifically designed for Multilingual Scene Text Image Super-Resolution. TextSR leverages a text detector to pinpoint text regions within an image and then employs Optical Character Recognition (OCR) to extract multilingual text from these areas. The extracted text characters are then transformed into visual shapes using a UTF-8 based text encoder and cross-attention. Recognizing that OCR may sometimes produce inaccurate results in real-world scenarios, we have developed two innovative methods to enhance the robustness of our model. By integrating text character priors with the low-resolution text images, our model effectively guides the super-resolution process, enhancing fine details within the text and improving overall legibility. The superior performance of our model on both the TextZoom and TextVQA datasets sets a new benchmark for STISR, underscoring the efficacy of our approach.		None
MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios	2025-05-27	Show Multimodal Large Language Models (MLLMs) have achieved considerable accuracy in Optical Character Recognition (OCR) from static images. However, their efficacy in video OCR is significantly diminished due to factors such as motion blur, temporal variations, and visual effects inherent in video content. To provide clearer guidance for training practical MLLMs, we introduce the MME-VideoOCR benchmark, which encompasses a comprehensive range of video OCR application scenarios. MME-VideoOCR features 10 task categories comprising 25 individual tasks and spans 44 diverse scenarios. These tasks extend beyond text recognition to incorporate deeper comprehension and reasoning of textual content within videos. The benchmark consists of 1,464 videos with varying resolutions, aspect ratios, and durations, along with 2,000 meticulously curated, manually annotated question-answer pairs. We evaluate 18 state-of-the-art MLLMs on MME-VideoOCR, revealing that even the best-performing model (Gemini-2.5 Pro) achieves an accuracy of only 73.7%. Fine-grained analysis indicates that while existing MLLMs demonstrate strong performance on tasks where relevant texts are contained within a single or few frames, they exhibit limited capability in effectively handling tasks that demand holistic video comprehension. These limitations are especially evident in scenarios that require spatio-temporal reasoning, cross-frame information integration, or resistance to language prior bias. Our findings also highlight the importance of high-resolution visual input and sufficient temporal coverage for reliable OCR in dynamic video scenarios.	preprint	None
PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy	2025-05-26	Show This paper introduces PreP-OCR, a two-stage pipeline that combines document image restoration with semantic-aware post-OCR correction to improve text extraction from degraded historical documents. Our key innovation lies in jointly optimizing image clarity and linguistic consistency. First, we generate synthetic image pairs with randomized text fonts, layouts, and degradations. An image restoration model is trained on this synthetic data, using multi-directional patch extraction and fusion to process large images. Second, a ByT5 post-corrector, fine-tuned on synthetic historical text training pairs, addresses any remaining OCR errors. Detailed experiments on 13,831 pages of real historical documents in English, French, and Spanish show that PreP-OCR pipeline reduces character error rates by 63.9-70.3% compared to OCR on raw images. Our pipeline demonstrates the potential of integrating image restoration with linguistic error correction for digitizing historical archives.	ACL 2025 main	None
TextFlux: An OCR-Free DiT Model for High-Fidelity Multilingual Scene Text Synthesis	2025-05-23	Show Diffusion-based scene text synthesis has progressed rapidly, yet existing methods commonly rely on additional visual conditioning modules and require large-scale annotated data to support multilingual generation. In this work, we revisit the necessity of complex auxiliary modules and further explore an approach that simultaneously ensures glyph accuracy and achieves high-fidelity scene integration, by leveraging diffusion models' inherent capabilities for contextual reasoning. To this end, we introduce TextFlux, a DiT-based framework that enables multilingual scene text synthesis. The advantages of TextFlux can be summarized as follows: (1) OCR-free model architecture. TextFlux eliminates the need for OCR encoders (additional visual conditioning modules) that are specifically used to extract visual text-related features. (2) Strong multilingual scalability. TextFlux is effective in low-resource multilingual settings, and achieves strong performance in newly added languages with fewer than 1,000 samples. (3) Streamlined training setup. TextFlux is trained with only 1% of the training data required by competing methods. (4) Controllable multi-line text generation. TextFlux offers flexible multi-line synthesis with precise line-level control, outperforming methods restricted to single-line or rigid layouts. Extensive experiments and visualizations demonstrate that TextFlux outperforms previous methods in both qualitative and quantitative evaluations.		None
OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning	2025-05-22	Show Recent advancements in multimodal slow-thinking systems have demonstrated remarkable performance across diverse visual reasoning tasks. However, their capabilities in text-rich image reasoning tasks remain understudied due to the lack of a systematic benchmark. To address this gap, we propose OCR-Reasoning, a comprehensive benchmark designed to systematically assess Multimodal Large Language Models on text-rich image reasoning tasks. The benchmark comprises 1,069 human-annotated examples spanning 6 core reasoning abilities and 18 practical reasoning tasks in text-rich visual scenarios. Furthermore, unlike other text-rich image understanding benchmarks that only annotate the final answers, OCR-Reasoning also annotates the reasoning process simultaneously. With the annotated reasoning process and the final answers, OCR-Reasoning evaluates not only the final answers generated by models but also their reasoning processes, enabling a holistic analysis of their problem-solving abilities. Leveraging this benchmark, we conducted a comprehensive evaluation of state-of-the-art MLLMs. Our results demonstrate the limitations of existing methodologies. Notably, even state-of-the-art MLLMs exhibit substantial difficulties, with none achieving accuracy surpassing 50% across OCR-Reasoning, indicating that the challenges of text-rich image reasoning are an urgent issue to be addressed. The benchmark and evaluation scripts are available at https://github.com/SCUT-DLVCLab/OCR-Reasoning.		Code Link
How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads	2025-05-21	Show Despite significant advancements in Large Vision Language Models (LVLMs), a gap remains, particularly regarding their interpretability and how they locate and interpret textual information within images. In this paper, we explore various LVLMs to identify the specific heads responsible for recognizing text from images, which we term the Optical Character Recognition Head (OCR Head). Our findings regarding these heads are as follows: (1) Less Sparse: Unlike previous retrieval heads, a large number of heads are activated to extract textual information from images. (2) Qualitatively Distinct: OCR heads possess properties that differ significantly from general retrieval heads, exhibiting low similarity in their characteristics. (3) Statically Activated: The frequency of activation for these heads closely aligns with their OCR scores. We validate our findings in downstream tasks by applying Chain-of-Thought (CoT) to both OCR and conventional retrieval heads and by masking these heads. We also demonstrate that redistributing sink-token values within the OCR heads improves performance. These insights provide a deeper understanding of the internal mechanisms LVLMs employ in processing embedded textual information in images.		None
Every Pixel Tells a Story: End-to-End Urdu Newspaper OCR	2025-05-20	Show This paper introduces a comprehensive end-to-end pipeline for Optical Character Recognition (OCR) on Urdu newspapers. In our approach, we address the unique challenges of complex multi-column layouts, low-resolution archival scans, and diverse font styles. Our process decomposes the OCR task into four key modules: (1) article segmentation, (2) image super-resolution, (3) column segmentation, and (4) text recognition. For article segmentation, we fine-tune and evaluate YOLOv11x to identify and separate individual articles from cluttered layouts. Our model achieves a precision of 0.963 and mAP@50 of 0.975. For super-resolution, we fine-tune and benchmark the SwinIR model (reaching 32.71 dB PSNR) to enhance the quality of degraded newspaper scans. To do our column segmentation, we use YOLOv11x to separate columns in text to further enhance performance - this model reaches a precision of 0.970 and mAP@50 of 0.975. In the text recognition stage, we benchmark a range of LLMs from different families, including Gemini, GPT, Llama, and Claude. The lowest WER of 0.133 is achieved by Gemini-2.5-Pro.		None
Reasoning-OCR: Can Large Multimodal Models Solve Complex Logical Reasoning Problems from OCR Cues?	2025-05-19	Show Large Multimodal Models (LMMs) have become increasingly versatile, accompanied by impressive Optical Character Recognition (OCR) related capabilities. Existing OCR-related benchmarks emphasize evaluating LMMs' abilities of relatively simple visual question answering, visual-text parsing, etc. However, the extent to which LMMs can deal with complex logical reasoning problems based on OCR cues is relatively unexplored. To this end, we introduce the Reasoning-OCR benchmark, which challenges LMMs to solve complex reasoning problems based on the cues that can be extracted from rich visual-text. Reasoning-OCR covers six visual scenarios and encompasses 150 meticulously designed questions categorized into six reasoning challenges. Additionally, Reasoning-OCR minimizes the impact of field-specialized knowledge. Our evaluation offers some insights for proprietary and open-source LMMs in different reasoning challenges, underscoring the urgent to improve the reasoning performance. We hope Reasoning-OCR can inspire and facilitate future research on enhancing complex reasoning ability based on OCR cues. Reasoning-OCR is publicly available at https://github.com/Hxyz-123/ReasoningOCR.		Code Link
Lost in OCR Translation? Vision-Based Approaches to Robust Document Retrieval	2025-05-08	Show Retrieval-Augmented Generation (RAG) has become a popular technique for enhancing the reliability and utility of Large Language Models (LLMs) by grounding responses in external documents. Traditional RAG systems rely on Optical Character Recognition (OCR) to first process scanned documents into text. However, even state-of-the-art OCRs can introduce errors, especially in degraded or complex documents. Recent vision-language approaches, such as ColPali, propose direct visual embedding of documents, eliminating the need for OCR. This study presents a systematic comparison between a vision-based RAG system (ColPali) and more traditional OCR-based pipelines utilizing Llama 3.2 (90B) and Nougat OCR across varying document qualities. Beyond conventional retrieval accuracy metrics, we introduce a semantic answer evaluation benchmark to assess end-to-end question-answering performance. Our findings indicate that while vision-based RAG performs well on documents it has been fine-tuned on, OCR-based RAG is better able to generalize to unseen documents of varying quality. We highlight the key trade-offs between computational efficiency and semantic accuracy, offering practical guidance for RAG practitioners in selecting between OCR-dependent and vision-based document retrieval systems in production environments.		None
Entropy Heat-Mapping: Localizing GPT-Based OCR Errors with Sliding-Window Shannon Analysis	2025-04-30	Show Vision-language models such as OpenAI GPT-4o can transcribe mathematical documents directly from images, yet their token-level confidence signals are seldom used to pinpoint local recognition mistakes. We present an entropy-heat-mapping proof-of-concept that turns per-token Shannon entropy into a visual ''uncertainty landscape''. By scanning the entropy sequence with a fixed-length sliding window, we obtain hotspots that are likely to contain OCR errors such as missing symbols, mismatched braces, or garbled prose. Using a small, curated set of scanned research pages rendered at several resolutions, we compare the highlighted hotspots with the actual transcription errors produced by GPT-4o. Our analysis shows that the vast majority of true errors are indeed concentrated inside the high-entropy regions. This study demonstrates--in a minimally engineered setting--that sliding-window entropy can serve as a practical, lightweight aid for post-editing GPT-based OCR. All code, sample data, and annotation guidelines are released to encourage replication and further research.	22 pages	None
DEVICE: Depth and Visual Concepts Aware Transformer for OCR-based Image Captioning	2025-04-26	Show OCR-based image captioning is an important but under-explored task, aiming to generate descriptions containing visual objects and scene text. Recent studies have made encouraging progress, but they are still suffering from a lack of overall understanding of scenes and generating inaccurate captions. One possible reason is that current studies mainly focus on constructing the plane-level geometric relationship of scene text without depth information. This leads to insufficient scene text relational reasoning so that models may describe scene text inaccurately. The other possible reason is that existing methods fail to generate fine-grained descriptions of some visual objects. In addition, they may ignore essential visual objects, leading to the scene text belonging to these ignored objects not being utilized. To address the above issues, we propose a Depth and Visual Concepts Aware Transformer (DEVICE) for OCR-based image captinong. Concretely, to construct three-dimensional geometric relations, we introduce depth information and propose a depth-enhanced feature updating module to ameliorate OCR token features. To generate more precise and comprehensive captions, we introduce semantic features of detected visual concepts as auxiliary information, and propose a semantic-guided alignment module to improve the model's ability to utilize visual concepts. Our DEVICE is capable of comprehending scenes more comprehensively and boosting the accuracy of described visual entities. Sufficient experiments demonstrate the effectiveness of our proposed DEVICE, which outperforms state-of-the-art models on the TextCaps test set.	13pag... 13pages, 8figures. This work has been published in Pattern Recognition	None
Guidelines for External Disturbance Factors in the Use of OCR in Real-World Environments	2025-04-21	Show The performance of OCR has improved with the evolution of AI technology. As OCR continues to broaden its range of applications, the increased likelihood of interference introduced by various usage environments can prevent it from achieving its inherent performance. This results in reduced recognition accuracy under certain conditions, and makes the quality control of recognition devices more challenging. Therefore, to ensure that users can properly utilize OCR, we compiled the real-world external disturbance factors that cause performance degradation, along with the resulting image degradation phenomena, into an external disturbance factor table and, by also indicating how to make use of it, organized them into guidelines.	16 pages, 14 figures	None
Evaluating Menu OCR and Translation: A Benchmark for Aligning Human and Automated Evaluations in Large Vision-Language Models	2025-04-16	Show The rapid advancement of large vision-language models (LVLMs) has significantly propelled applications in document understanding, particularly in optical character recognition (OCR) and multilingual translation. However, current evaluations of LVLMs, like the widely used OCRBench, mainly focus on verifying the correctness of their short-text responses and long-text responses with simple layout, while the evaluation of their ability to understand long texts with complex layout design is highly significant but largely overlooked. In this paper, we propose Menu OCR and Translation Benchmark (MOTBench), a specialized evaluation framework emphasizing the pivotal role of menu translation in cross-cultural communication. MOTBench requires LVLMs to accurately recognize and translate each dish, along with its price and unit items on a menu, providing a comprehensive assessment of their visual understanding and language processing capabilities. Our benchmark is comprised of a collection of Chinese and English menus, characterized by intricate layouts, a variety of fonts, and culturally specific elements across different languages, along with precise human annotations. Experiments show that our automatic evaluation results are highly consistent with professional human evaluation. We evaluate a range of publicly available state-of-the-art LVLMs, and through analyzing their output to identify the strengths and weaknesses in their performance, offering valuable insights to guide future advancements in LVLM development. MOTBench is available at https://github.com/gitwzl/MOTBench.	12 pa... 12 pages, 5 figures, 5 Tables	Code Link
Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR	2025-04-15	Show The Optical Character Recognition (OCR) task is important for evaluating Vision-Language Models (VLMs) and providing high-quality data sources for LLM training data. While state-of-the-art VLMs show improved average OCR accuracy, they still struggle with sample-level quality degradation and lack reliable automatic detection of low-quality outputs. We introduce Consensus Entropy (CE), a training-free post-inference method that quantifies OCR uncertainty by aggregating outputs from multiple VLMs. Our approach exploits a key insight: correct VLM OCR predictions converge in output space while errors diverge. We develop a lightweight multi-model framework that effectively identifies problematic samples, selects the best outputs and combines model strengths. Experiments across multiple OCR benchmarks and VLMs demonstrate that CE outperforms VLM-as-judge approaches and single-model baselines at the same cost and achieves state-of-the-art results across multiple metrics. For instance, our solution demonstrates: achieving 15.2% higher F1 scores than VLM-as-judge methods in quality verification, delivering 6.0% accuracy gains on mathematical calculation tasks, and requiring rephrasing only 7.3% of inputs while maintaining overall performance. Notably, the entire process requires neither training nor supervision while maintaining plug-and-play functionality throughout.		None
QID: Efficient Query-Informed ViTs in Data-Scarce Regimes for OCR-free Visual Document Understanding	2025-04-07	Show In Visual Document Understanding (VDU) tasks, fine-tuning a pre-trained Vision-Language Model (VLM) with new datasets often falls short in optimizing the vision encoder to identify query-specific regions in text-rich document images. Existing methods that directly inject queries into model layers by modifying the network architecture often struggle to adapt to new datasets with limited annotations. To address this, we introduce QID, a novel, streamlined, architecture-preserving approach that integrates query embeddings into the vision encoder, leading to notable performance gains, particularly in data-scarce fine-tuning scenarios. Specifically, our approach introduces a dual-module framework: a query-aware module that generates a unique query vector to precisely guide the model's focus, as well as a query-agnostic module that captures the positional relationships among tokens, ensuring robust spatial understanding. Notably, both modules operate independently of the vision attention blocks, facilitating targeted learning of query embeddings and enhancing visual semantic identification. Experiments with OCR-free VLMs across multiple datasets demonstrate significant performance improvements using our method, especially in handling text-rich documents in data-scarce environments.	8 pag... 8 pages, accepted by CVPR 2025 MULA	None
VISTA-OCR: Towards generative and interactive end to end OCR models	2025-04-04	Show We introduce \textbf{VISTA-OCR} (Vision and Spatially-aware Text Analysis OCR), a lightweight architecture that unifies text detection and recognition within a single generative model. Unlike conventional methods that require separate branches with dedicated parameters for text recognition and detection, our approach leverages a Transformer decoder to sequentially generate text transcriptions and their spatial coordinates in a unified branch. Built on an encoder-decoder architecture, VISTA-OCR is progressively trained, starting with the visual feature extraction phase, followed by multitask learning with multimodal token generation. To address the increasing demand for versatile OCR systems capable of advanced tasks, such as content-based text localization \ref{content_based_localization}, we introduce new prompt-controllable OCR tasks during pre-training.To enhance the model's capabilities, we built a new dataset composed of real-world examples enriched with bounding box annotations and synthetic samples. Although recent Vision Large Language Models (VLLMs) can efficiently perform these tasks, their high computational cost remains a barrier for practical deployment. In contrast, our VISTA$_{\text{omni}}$ variant processes both handwritten and printed documents with only 150M parameters, interactively, by prompting. Extensive experiments on multiple datasets demonstrate that VISTA-OCR achieves better performance compared to state-of-the-art specialized models on standard OCR tasks while showing strong potential for more sophisticated OCR applications, addressing the growing need for interactive OCR systems. All code and annotations for VISTA-OCR will be made publicly available upon acceptance.		None
Multimodal LLMs for OCR, OCR Post-Correction, and Named Entity Recognition in Historical Documents	2025-04-01	Show We explore how multimodal Large Language Models (mLLMs) can help researchers transcribe historical documents, extract relevant historical information, and construct datasets from historical sources. Specifically, we investigate the capabilities of mLLMs in performing (1) Optical Character Recognition (OCR), (2) OCR Post-Correction, and (3) Named Entity Recognition (NER) tasks on a set of city directories published in German between 1754 and 1870. First, we benchmark the off-the-shelf transcription accuracy of both mLLMs and conventional OCR models. We find that the best-performing mLLM model significantly outperforms conventional state-of-the-art OCR models and other frontier mLLMs. Second, we are the first to introduce multimodal post-correction of OCR output using mLLMs. We find that this novel approach leads to a drastic improvement in transcription accuracy and consistently produces highly accurate transcriptions (<1% CER), without any image pre-processing or model fine-tuning. Third, we demonstrate that mLLMs can efficiently recognize entities in transcriptions of historical documents and parse them into structured dataset formats. Our findings provide early evidence for the long-term potential of mLLMs to introduce a paradigm shift in the approaches to historical data collection and document transcription.		None
Context-Independent OCR with Multimodal LLMs: Effects of Image Resolution and Visual Complexity	2025-03-31	Show Due to their high versatility in tasks such as image captioning, document analysis, and automated content generation, multimodal Large Language Models (LLMs) have attracted significant attention across various industrial fields. In particular, they have been shown to surpass specialized models in Optical Character Recognition (OCR). Nevertheless, their performance under different image conditions remains insufficiently investigated, and individual character recognition is not guaranteed due to their reliance on contextual cues. In this work, we examine a context-independent OCR task using single-character images with diverse visual complexities to determine the conditions for accurate recognition. Our findings reveal that multimodal LLMs can match conventional OCR methods at about 300 ppi, yet their performance deteriorates significantly below 150 ppi. Additionally, we observe a very weak correlation between visual complexity and misrecognitions, whereas a conventional OCR-specific model exhibits no correlation. These results suggest that image resolution and visual complexity may play an important role in the reliable application of multimodal LLMs to OCR tasks that require precise character-level accuracy.		None
VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document Understanding	2025-03-25	Show In recent years, notable advancements have been made in the domain of visual document understanding, with the prevailing architecture comprising a cascade of vision and language models. The text component can either be extracted explicitly with the use of external OCR models in OCR-based approaches, or alternatively, the vision model can be endowed with reading capabilities in OCR-free approaches. Typically, the queries to the model are input exclusively to the language component, necessitating the visual features to encompass the entire document. In this paper, we present VisFocus, an OCR-free method designed to better exploit the vision encoder's capacity by coupling it directly with the language prompt. To do so, we replace the down-sampling layers with layers that receive the input prompt and allow highlighting relevant parts of the document, while disregarding others. We pair the architecture enhancements with a novel pre-training task, using language masking on a snippet of the document text fed to the visual encoder in place of the prompt, to empower the model with focusing capabilities. Consequently, VisFocus learns to allocate its attention to text patches pertinent to the provided prompt. Our experiments demonstrate that this prompt-guided visual encoding approach significantly improves performance, achieving state-of-the-art results on various benchmarks.	ECCV ... ECCV 2024, official code at https://github.com/amazon-science/visfocus	Code Link
KAP: MLLM-assisted OCR Text Enhancement for Hybrid Retrieval in Chinese Non-Narrative Documents	2025-03-11	Show We propose Knowledge-Aware Preprocessing (KAP), a two-stage preprocessing framework tailored for Traditional Chinese non-narrative documents, designed to enhance retrieval accuracy in Hybrid Retrieval systems. Hybrid Retrieval, which integrates Sparse Retrieval (e.g., BM25) and Dense Retrieval (e.g., vector embeddings), has become a widely adopted approach for improving search effectiveness. However, its performance heavily depends on the quality of input text, which is often degraded when dealing with non-narrative documents such as PDFs containing financial statements, contractual clauses, and tables. KAP addresses these challenges by integrating Multimodal Large Language Models (MLLMs) with LLM-driven post-OCR processing, refining extracted text to reduce OCR noise, restore table structures, and optimize text format. By ensuring better compatibility with Hybrid Retrieval, KAP improves the accuracy of both Sparse and Dense Retrieval methods without modifying the retrieval architecture itself.		None
OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation	2025-03-11	Show Retrieval-augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge to reduce hallucinations and incorporate up-to-date information without retraining. As an essential part of RAG, external knowledge bases are commonly built by extracting structured data from unstructured PDF documents using Optical Character Recognition (OCR). However, given the imperfect prediction of OCR and the inherent non-uniform representation of structured data, knowledge bases inevitably contain various OCR noises. In this paper, we introduce OHRBench, the first benchmark for understanding the cascading impact of OCR on RAG systems. OHRBench includes 8,561 carefully selected unstructured document images from seven real-world RAG application domains, along with 8,498 Q&A pairs derived from multimodal elements in documents, challenging existing OCR solutions used for RAG. To better understand OCR's impact on RAG systems, we identify two primary types of OCR noise: Semantic Noise and Formatting Noise and apply perturbation to generate a set of structured data with varying degrees of each OCR noise. Using OHRBench, we first conduct a comprehensive evaluation of current OCR solutions and reveal that none is competent for constructing high-quality knowledge bases for RAG systems. We then systematically evaluate the impact of these two noise types and demonstrate the trend relationship between the degree of OCR noise and RAG performance. Our OHRBench, including PDF documents, Q&As, and the ground truth structured data are released at: https://github.com/opendatalab/OHR-Bench	Work in progress	Code Link
Reference-Based Post-OCR Processing with LLM for Precise Diacritic Text in Historical Document Recognition	2025-02-27	Show Extracting fine-grained OCR text from aged documents in diacritic languages remains challenging due to unexpected artifacts, time-induced degradation, and lack of datasets. While standalone spell correction approaches have been proposed, they show limited performance for historical documents due to numerous possible OCR error combinations and differences between modern and classical corpus distributions. We propose a method utilizing available content-focused ebooks as a reference base to correct imperfect OCR-generated text, supported by large language models. This technique generates high-precision pseudo-page-to-page labels for diacritic languages, where small strokes pose significant challenges in historical conditions. The pipeline eliminates various types of noise from aged documents and addresses issues such as missing characters, words, and disordered sequences. Our post-processing method, which generated a large OCR dataset of classical Vietnamese books, achieved a mean grading score of 8.72 on a 10-point scale. This outperformed the state-of-the-art transformer-based Vietnamese spell correction model, which scored 7.03 when evaluated on a sampled subset of the dataset. We also trained a baseline OCR model to assess and compare it with well-known engines. Experimental results demonstrate the strength of our baseline model compared to widely used open-source solutions. The resulting dataset will be released publicly to support future studies.	Accep... Accepted in the AAAI 2025 (39th) AISI track. Dataset and repo are in the paper	None
MultiOCR-QA: Dataset for Evaluating Robustness of LLMs in Question Answering on Multilingual OCR Texts	2025-02-24	Show Optical Character Recognition (OCR) plays a crucial role in digitizing historical and multilingual documents, yet OCR errors -- imperfect extraction of the text, including character insertion, deletion and permutation -- can significantly impact downstream tasks like question-answering (QA). In this work, we introduce a multilingual QA dataset MultiOCR-QA, designed to analyze the effects of OCR noise on QA systems' performance. The MultiOCR-QA dataset comprises 60K question-answer pairs covering three languages, English, French, and German. The dataset is curated from OCR-ed old documents, allowing for the evaluation of OCR-induced challenges on question answering. We evaluate MultiOCR-QA on various levels and types of OCR errors to access the robustness of LLMs in handling real-world digitization errors. Our findings show that QA systems are highly prone to OCR induced errors and exhibit performance degradation on noisy OCR text.		None
RoundTripOCR: A Data Generation Technique for Enhancing Post-OCR Error Correction in Low-Resource Devanagari Languages	2025-02-23	Show Optical Character Recognition (OCR) technology has revolutionized the digitization of printed text, enabling efficient data extraction and analysis across various domains. Just like Machine Translation systems, OCR systems are prone to errors. In this work, we address the challenge of data generation and post-OCR error correction, specifically for low-resource languages. We propose an approach for synthetic data generation for Devanagari languages, RoundTripOCR, that tackles the scarcity of the post-OCR Error Correction datasets for low-resource languages. We release post-OCR text correction datasets for Hindi, Marathi, Bodo, Nepali, Konkani and Sanskrit. We also present a novel approach for OCR error correction by leveraging techniques from machine translation. Our method involves translating erroneous OCR output into a corrected form by treating the OCR errors as mistranslations in a parallel text corpus, employing pre-trained transformer models to learn the mapping from erroneous to correct text pairs, effectively correcting OCR errors.	Proce... Proceedings of the 21st International Conference on Natural Language Processing (ICON)	None
KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding	2025-02-20	Show With the growing adoption of Retrieval-Augmented Generation (RAG) in document processing, robust text recognition has become increasingly critical for knowledge extraction. While OCR (Optical Character Recognition) for English and other languages benefits from large datasets and well-established benchmarks, Arabic OCR faces unique challenges due to its cursive script, right-to-left text flow, and complex typographic and calligraphic features. We present KITAB-Bench, a comprehensive Arabic OCR benchmark that fills the gaps in current evaluation systems. Our benchmark comprises 8,809 samples across 9 major domains and 36 sub-domains, encompassing diverse document types including handwritten text, structured tables, and specialized coverage of 21 chart types for business intelligence. Our findings show that modern vision-language models (such as GPT-4, Gemini, and Qwen) outperform traditional OCR approaches (like EasyOCR, PaddleOCR, and Surya) by an average of 60% in Character Error Rate (CER). Furthermore, we highlight significant limitations of current Arabic OCR models, particularly in PDF-to-Markdown conversion, where the best model Gemini-2.0-Flash achieves only 65% accuracy. This underscores the challenges in accurately recognizing Arabic text, including issues with complex fonts, numeral recognition errors, word elongation, and table structure detection. This work establishes a rigorous evaluation framework that can drive improvements in Arabic document analysis methods and bridge the performance gap with English OCR technologies.	17 pa... 17 pages, 5 figures, ACL 2025	None
OCR Error Post-Correction with LLMs in Historical Documents: No Free Lunches	2025-02-03	Show Optical Character Recognition (OCR) systems often introduce errors when transcribing historical documents, leaving room for post-correction to improve text quality. This study evaluates the use of open-weight LLMs for OCR error correction in historical English and Finnish datasets. We explore various strategies, including parameter optimization, quantization, segment length effects, and text continuation methods. Our results demonstrate that while modern LLMs show promise in reducing character error rates (CER) in English, a practically useful performance for Finnish was not reached. Our findings highlight the potential and limitations of LLMs in scaling OCR post-correction for large historical corpora.	To be... To be published in RESOURCEFUL 2025	None
Ocean-OCR: Towards General OCR Application via a Vision-Language Model	2025-01-26	Show Multimodal large language models (MLLMs) have shown impressive capabilities across various domains, excelling in processing and understanding information from multiple modalities. Despite the rapid progress made previously, insufficient OCR ability hinders MLLMs from excelling in text-related tasks. In this paper, we present \textbf{Ocean-OCR}, a 3B MLLM with state-of-the-art performance on various OCR scenarios and comparable understanding ability on general tasks. We employ Native Resolution ViT to enable variable resolution input and utilize a substantial collection of high-quality OCR datasets to enhance the model performance. We demonstrate the superiority of Ocean-OCR through comprehensive experiments on open-source OCR benchmarks and across various OCR scenarios. These scenarios encompass document understanding, scene text recognition, and handwritten recognition, highlighting the robust OCR capabilities of Ocean-OCR. Note that Ocean-OCR is the first MLLM to outperform professional OCR models such as TextIn and PaddleOCR.		None
CLOCR-C: Context Leveraging OCR Correction with Pre-trained Language Models	2025-01-22	Show The digitisation of historical print media archives is crucial for increasing accessibility to contemporary records. However, the process of Optical Character Recognition (OCR) used to convert physical records to digital text is prone to errors, particularly in the case of newspapers and periodicals due to their complex layouts. This paper introduces Context Leveraging OCR Correction (CLOCR-C), which utilises the infilling and context-adaptive abilities of transformer-based language models (LMs) to improve OCR quality. The study aims to determine if LMs can perform post-OCR correction, improve downstream NLP tasks, and the value of providing the socio-cultural context as part of the correction process. Experiments were conducted using seven LMs on three datasets: the 19th Century Serials Edition (NCSE) and two datasets from the Overproof collection. The results demonstrate that some LMs can significantly reduce error rates, with the top-performing model achieving over a 60% reduction in character error rate on the NCSE dataset. The OCR improvements extend to downstream tasks, such as Named Entity Recognition, with increased Cosine Named Entity Similarity. Furthermore, the study shows that providing socio-cultural context in the prompts improves performance, while misleading prompts lower performance. In addition to the findings, this study releases a dataset of 91 transcribed articles from the NCSE, containing a total of 40 thousand words, to support further research in this area. The findings suggest that CLOCR-C is a promising approach for enhancing the quality of existing digital archives by leveraging the socio-cultural information embedded in the LMs and the text requiring correction.	20 pages, 2 figures,	None
Early evidence of how LLMs outperform traditional systems on OCR/HTR tasks for historical records	2025-01-20	Show We explore the ability of two LLMs -- GPT-4o and Claude Sonnet 3.5 -- to transcribe historical handwritten documents in a tabular format and compare their performance to traditional OCR/HTR systems: EasyOCR, Keras, Pytesseract, and TrOCR. Considering the tabular form of the data, two types of experiments are executed: one where the images are split line by line and the other where the entire scan is used as input. Based on CER and BLEU, we demonstrate that LLMs outperform the conventional OCR/HTR methods. Moreover, we also compare the evaluated CER and BLEU scores to human evaluations to better judge the outputs of whole-scan experiments and understand influential factors for CER and BLEU. Combining judgments from all the evaluation metrics, we conclude that two-shot GPT-4o for line-by-line images and two-shot Claude Sonnet 3.5 for whole-scan images yield the transcriptions of the historical records most similar to the ground truth.	15 pages, 7 figures	None
Jochre 3 and the Yiddish OCR corpus	2025-01-14	Show We describe the construction of a publicly available Yiddish OCR Corpus, and describe and evaluate the open source OCR tool suite Jochre 3, including an Alto editor for corpus annotation, OCR software for Alto OCR layer generation, and a customizable OCR search engine. The current version of the Yiddish OCR corpus contains 658 pages, 186K tokens and 840K glyphs. The Jochre 3 OCR tool uses various fine-tuned YOLOv8 models for top-down page layout analysis, and a custom CNN network for glyph recognition. It attains a CER of 1.5% on our test corpus, far out-performing all other existing public models for Yiddish. We analyzed the full 660M word Yiddish Book Center with Jochre 3 OCR, and the new OCR is searchable through the Yiddish Book Center OCR search engine.	10 pages, 4 figures	None
Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study	2024-12-29	Show With the rise of multimodal large language models, accurately extracting and understanding textual information from video content, referred to as video based optical character recognition (Video OCR), has become a crucial capability. This paper introduces a novel benchmark designed to evaluate the video OCR performance of multi-modal models in videos. Comprising 1,028 videos and 2,961 question-answer pairs, this benchmark proposes several key challenges through 6 distinct subtasks: (1) Recognition of text content itself and its basic visual attributes, (2)Semantic and Spatial Comprehension of OCR objects in videos (3) Dynamic Motion detection and Temporal Localization. We developed this benchmark using a semi-automated approach that integrates the OCR ability of image LLMs with manual refinement, balancing efficiency, cost, and data quality. Our resource aims to help advance research in video LLMs and underscores the need for improving OCR ability for video LLMs. The benchmark will be released on https://github.com/YuHuiGao/FG-Bench.git.	Accep... Accepted by CoLing 2025 (The 31st International Conference on Computational Linguistics)	Code Link
ERPA: Efficient RPA Model Integrating OCR and LLMs for Intelligent Document Processing	2024-12-24	Show This paper presents ERPA, an innovative Robotic Process Automation (RPA) model designed to enhance ID data extraction and optimize Optical Character Recognition (OCR) tasks within immigration workflows. Traditional RPA solutions often face performance limitations when processing large volumes of documents, leading to inefficiencies. ERPA addresses these challenges by incorporating Large Language Models (LLMs) to improve the accuracy and clarity of extracted text, effectively handling ambiguous characters and complex structures. Benchmark comparisons with leading platforms like UiPath and Automation Anywhere demonstrate that ERPA significantly reduces processing times by up to 94 percent, completing ID data extraction in just 9.94 seconds. These findings highlight ERPA's potential to revolutionize document automation, offering a faster and more reliable alternative to current RPA solutions.	6 pag... 6 pages , 2 figures, 1 algorithm	None
LMRPA: Large Language Model-Driven Efficient Robotic Process Automation for OCR	2024-12-24	Show This paper introduces LMRPA, a novel Large Model-Driven Robotic Process Automation (RPA) model designed to greatly improve the efficiency and speed of Optical Character Recognition (OCR) tasks. Traditional RPA platforms often suffer from performance bottlenecks when handling high-volume repetitive processes like OCR, leading to a less efficient and more time-consuming process. LMRPA allows the integration of Large Language Models (LLMs) to improve the accuracy and readability of extracted text, overcoming the challenges posed by ambiguous characters and complex text structures.Extensive benchmarks were conducted comparing LMRPA to leading RPA platforms, including UiPath and Automation Anywhere, using OCR engines like Tesseract and DocTR. The results are that LMRPA achieves superior performance, cutting the processing times by up to 52%. For instance, in Batch 2 of the Tesseract OCR task, LMRPA completed the process in 9.8 seconds, where UiPath finished in 18.1 seconds and Automation Anywhere finished in 18.7 seconds. Similar improvements were observed with DocTR, where LMRPA outperformed other automation tools conducting the same process by completing tasks in 12.7 seconds, while competitors took over 20 seconds to do the same. These findings highlight the potential of LMRPA to revolutionize OCR-driven automation processes, offering a more efficient and effective alternative solution to the existing state-of-the-art RPA models.	10 pa... 10 pages , 1 figure , 1 algorithm	None
Deciphering the Underserved: Benchmarking LLM OCR for Low-Resource Scripts	2024-12-20	Show This study investigates the potential of Large Language Models (LLMs), particularly GPT-4o, for Optical Character Recognition (OCR) in low-resource scripts such as Urdu, Albanian, and Tajik, with English serving as a benchmark. Using a meticulously curated dataset of 2,520 images incorporating controlled variations in text length, font size, background color, and blur, the research simulates diverse real-world challenges. Results emphasize the limitations of zero-shot LLM-based OCR, particularly for linguistically complex scripts, highlighting the need for annotated datasets and fine-tuned models. This work underscores the urgency of addressing accessibility gaps in text digitization, paving the way for inclusive and robust OCR solutions for underserved languages.		None
Towards Deployable OCR models for Indic languages	2024-12-18	Show Recognition of text on word or line images, without the need for sub-word segmentation has become the mainstream of research and development of text recognition for Indian languages. Modelling unsegmented sequences using Connectionist Temporal Classification (CTC) is the most commonly used approach for segmentation-free OCR. In this work we present a comprehensive empirical study of various neural network models that uses CTC for transcribing step-wise predictions in the neural network output to a Unicode sequence. The study is conducted for 13 Indian languages, using an internal dataset that has around 1000 pages per language. We study the choice of line vs word as the recognition unit, and use of synthetic data to train the models. We compare our models with popular publicly available OCR tools for end-to-end document image recognition. Our end-to-end pipeline that employ our recognition models and existing text segmentation tools outperform these public OCR tools for 8 out of the 13 languages. We also introduce a new public dataset called Mozhi for word and line recognition in Indian language. The dataset contains more than 1.2 million annotated word images (120 thousand text lines) across 13 Indian languages. Our code, trained models and the Mozhi dataset will be made available at http://cvit.iiit.ac.in/research/projects/cvit-projects/	prese... presented at ICPR 2024; https://link.springer.com/chapter/10.1007/978-3-031-78495-8_11	None
Vehicle Detection and Classification for Toll collection using YOLOv11 and Ensemble OCR	2024-12-13	Show Traditional automated toll collection systems depend on complex hardware configurations, that require huge investments in installation and maintenance. This research paper presents an innovative approach to revolutionize automated toll collection by using a single camera per plaza with the YOLOv11 computer vision architecture combined with an ensemble OCR technique. Our system has achieved a Mean Average Precision (mAP) of 0.895 over a wide range of conditions, demonstrating 98.5% accuracy in license plate recognition, 94.2% accuracy in axle detection, and 99.7% OCR confidence scoring. The architecture incorporates intelligent vehicle tracking across IOU regions, automatic axle counting by way of spatial wheel detection patterns, and real-time monitoring through an extended dashboard interface. Extensive training using 2,500 images under various environmental conditions, our solution shows improved performance while drastically reducing hardware resources compared to conventional systems. This research contributes toward intelligent transportation systems by introducing a scalable, precision-centric solution that improves operational efficiency and user experience in modern toll collections.		None
CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy	2024-12-10	Show Large Multimodal Models (LMMs) have demonstrated impressive performance in recognizing document images with natural language instructions. However, it remains unclear to what extent capabilities in literacy with rich structure and fine-grained visual challenges. The current landscape lacks a comprehensive benchmark to effectively measure the literate capabilities of LMMs. Existing benchmarks are often limited by narrow scenarios and specified tasks. To this end, we introduce CC-OCR, a comprehensive benchmark that possesses a diverse range of scenarios, tasks, and challenges. CC-OCR comprises four OCR-centric tracks: multi-scene text reading, multilingual text reading, document parsing, and key information extraction. It includes 39 subsets with 7,058 full annotated images, of which 41% are sourced from real applications, and released for the first time. We evaluate nine prominent LMMs and reveal both the strengths and weaknesses of these models, particularly in text grounding, multi-orientation, and hallucination of repetition. CC-OCR aims to comprehensively evaluate the capabilities of LMMs on OCR-centered tasks, facilitating continued progress in this crucial area.	23 pa... 23 pages, 14 figures; The code will be released soon	None
Assessing GPT Model Uncertainty in Mathematical OCR Tasks via Entropy Analysis	2024-12-08	Show This paper investigates the uncertainty of Generative Pre-trained Transformer (GPT) models in extracting mathematical equations from images of varying resolutions and converting them into LaTeX code. We employ concepts of entropy and mutual information to examine the recognition process and assess the model's uncertainty in this Optical Character Recognition (OCR) task. By analyzing the conditional entropy of the output token sequences, we provide both theoretical insights and practical measurements of the GPT model's performance given different image qualities. Our experimental results, obtained using a Python implementation available on GitHub, demonstrate a clear relationship between image resolution and GPT model uncertainty. Higher-resolution images lead to lower entropy values, indicating reduced uncertainty and improved accuracy in the recognized LaTeX code. Conversely, lower-resolution images result in increased entropy, reflecting higher uncertainty and a higher likelihood of recognition errors. These findings highlight the practical importance of considering image quality in GPT-based mathematical OCR applications and demonstrate how entropy analysis, grounded in information-theoretic concepts, can effectively quantify model uncertainty in real-world tasks.	21 pages	None
Arabic Handwritten Document OCR Solution with Binarization and Adaptive Scale Fusion Detection	2024-12-02	Show The problem of converting images of text into plain text is a widely researched topic in both academia and industry. Arabic handwritten Text Recognation (AHTR) poses additional challenges due to diverse handwriting styles and limited labeled data. In this paper we present a complete OCR pipeline that starts with line segmentation using Differentiable Binarization and Adaptive Scale Fusion techniques to ensure accurate detection of text lines. Following segmentation, a CNN-BiLSTM-CTC architecture is applied to recognize characters. Our system, trained on the Arabic Multi-Fonts Dataset (AMFDS), achieves a Character Recognition Rate (CRR) of 99.20% and a Word Recognition Rate (WRR) of 93.75% on single-word samples containing 7 to 10 characters, along with a CRR of 83.76% for sentences. These results demonstrate the system's strong performance in handling Arabic scripts, establishing a new benchmark for AHTR systems.		None
Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown Extraction	2024-11-19	Show We present Arabic-Nougat, a suite of OCR models for converting Arabic book pages into structured Markdown text. Based on Meta's Nougat architecture, Arabic-Nougat includes three specialized models: arabic-small-nougat, arabic-base-nougat, and arabic-large-nougat. These models are fine-tuned on a synthetic dataset, arabic-img2md, comprising 13.7k pairs of Arabic book pages and their Markdown representations. Key contributions include the Aranizer-PBE-86k tokenizer, designed for efficient tokenization, and the use of torch.bfloat16 precision with Flash Attention 2 for optimized training and inference. Our models achieve state-of-the-art performance, with arabic-large-nougat delivering the highest Markdown Structure Accuracy and the lowest Character Error Rate. Additionally, we release a large-scale dataset containing 1.1 billion Arabic tokens extracted from over 8,500 books using our best-performing model, providing a valuable resource for Arabic OCR research. All models, datasets, and code are open-sourced and available at https://github.com/MohamedAliRashad/arabic-nougat.	7 pages, 1 figure	Code Link
Investigating OCR-Sensitive Neurons to Improve Entity Recognition in Historical Documents	2024-11-18	Show This paper investigates the presence of OCR-sensitive neurons within the Transformer architecture and their influence on named entity recognition (NER) performance on historical documents. By analysing neuron activation patterns in response to clean and noisy text inputs, we identify and then neutralise OCR-sensitive neurons to improve model performance. Based on two open access large language models (Llama2 and Mistral), experiments demonstrate the existence of OCR-sensitive regions and show improvements in NER performance on historical newspapers and classical commentaries, highlighting the potential of targeted neuron modulation to improve models' performance on noisy text.		None
Towards Accessible Learning: Deep Learning-Based Potential Dysgraphia Detection and OCR for Potentially Dysgraphic Handwriting	2024-11-18	Show Dysgraphia is a learning disorder that affects handwriting abilities, making it challenging for children to write legibly and consistently. Early detection and monitoring are crucial for providing timely support and interventions. This study applies deep learning techniques to address the dual tasks of dysgraphia detection and optical character recognition (OCR) on handwriting samples from children with potential dysgraphic symptoms. Using a dataset of handwritten samples from Malaysian schoolchildren, we developed a custom Convolutional Neural Network (CNN) model, alongside VGG16 and ResNet50, to classify handwriting as dysgraphic or non-dysgraphic. The custom CNN model outperformed the pre-trained models, achieving a test accuracy of 91.8% with high precision, recall, and AUC, demonstrating its robustness in identifying dysgraphic handwriting features. Additionally, an OCR pipeline was created to segment and recognize individual characters in dysgraphic handwriting, achieving a character recognition accuracy of approximately 43.5%. This research highlights the potential of deep learning in supporting dysgraphia assessment, laying a foundation for tools that could assist educators and clinicians in identifying dysgraphia and tracking handwriting progress over time. The findings contribute to advancements in assistive technologies for learning disabilities, offering hope for more accessible and accurate diagnostic tools in educational and clinical settings.		None
Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding	2024-11-08	Show We present a novel OCR-free document understanding framework based on pretrained Multimodal Large Language Models (MLLMs). Our approach employs multi-scale visual features to effectively handle various font sizes within document images. To address the increasing costs of considering the multi-scale visual inputs for MLLMs, we propose the Hierarchical Visual Feature Aggregation (HVFA) module, designed to reduce the number of input tokens to LLMs. Leveraging a feature pyramid with cross-attentive pooling, our approach effectively manages the trade-off between information loss and efficiency without being affected by varying document image sizes. Furthermore, we introduce a novel instruction tuning task, which facilitates the model's text-reading capability by learning to predict the relative positions of input text, eventually minimizing the risk of truncated text caused by the limited capacity of LLMs. Comprehensive experiments validate the effectiveness of our approach, demonstrating superior performance in various document understanding tasks.	NeurIPS 2024	None
Comparison of Image Preprocessing Techniques for Vehicle License Plate Recognition Using OCR: Performance and Accuracy Evaluation	2024-10-15	Show The growing use of Artificial Intelligence solutions has led to an explosion in image capture and its application in machine learning models. However, the lack of standardization in image quality generates inconsistencies in the results of these models. To mitigate this problem, Optical Character Recognition (OCR) is often used as a preprocessing technique, but it still faces challenges in scenarios with inadequate lighting, low resolution, and perspective distortions. This work aims to explore and evaluate various preprocessing techniques, such as grayscale conversion, CLAHE in RGB, and Bilateral Filter, applied to vehicle license plate recognition. Each technique is analyzed individually and in combination, using metrics such as accuracy, precision, recall, F1-score, ROC curve, AUC, and ANOVA, to identify the most effective method. The study uses a dataset of Brazilian vehicle license plates, widely used in OCR applications. The research provides a detailed analysis of best preprocessing practices, offering insights to optimize OCR performance in real-world scenarios.	12 pages, 13 figures	None
Mero Nagarikta: Advanced Nepali Citizenship Data Extractor with Deep Learning-Powered Text Detection and OCR	2024-10-08	Show Transforming text-based identity documents, such as Nepali citizenship cards, into a structured digital format poses several challenges due to the distinct characteristics of the Nepali script and minor variations in print alignment and contrast across different cards. This work proposes a robust system using YOLOv8 for accurate text object detection and an OCR algorithm based on Optimized PyTesseract. The system, implemented within the context of a mobile application, allows for the automated extraction of important textual information from both the front and the back side of Nepali citizenship cards, including names, citizenship numbers, and dates of birth. The final YOLOv8 model was accurate, with a mean average precision of 99.1% for text detection on the front and 96.1% on the back. The tested PyTesseract optimized for Nepali characters outperformed the standard OCR regarding flexibility and accuracy, extracting text from images with clean and noisy backgrounds and various contrasts. Using preprocessing steps such as converting the images into grayscale, removing noise from the images, and detecting edges further improved the system's OCR accuracy, even for low-quality photos. This work expands the current body of research in multilingual OCR and document analysis, especially for low-resource languages such as Nepali. It emphasizes the effectiveness of combining the latest object detection framework with OCR models that have been fine-tuned for practical applications.	13 pages, 8 figures	None
TextHawk2: A Large Vision-Language Model Excels in Bilingual OCR and Grounding with 16x Fewer Tokens	2024-10-07	Show Reading dense text and locating objects within images are fundamental abilities for Large Vision-Language Models (LVLMs) tasked with advanced jobs. Previous LVLMs, including superior proprietary models like GPT-4o, have struggled to excel in both tasks simultaneously. Moreover, previous LVLMs with fine-grained perception cost thousands of tokens per image, making them resource-intensive. We present TextHawk2, a bilingual LVLM featuring efficient fine-grained perception and demonstrating cutting-edge performance across general-purpose, OCR, and grounding tasks with 16 times fewer image tokens. Critical improvements include: (1) Token Compression: Building on the efficient architecture of its predecessor, TextHawk2 significantly reduces the number of tokens per image by 16 times, facilitating training and deployment of the TextHawk series with minimal resources. (2) Visual Encoder Reinforcement: We enhance the visual encoder through LVLM co-training, unlocking its potential for previously unseen tasks like Chinese OCR and grounding. (3) Data Diversity: We maintain a comparable scale of 100 million samples while diversifying the sources of pre-training data. We assess TextHawk2 across multiple benchmarks, where it consistently delivers superior performance and outperforms closed-source models of similar scale, such as achieving 78.4% accuracy on OCRBench, 81.4% accuracy on ChartQA, 89.6% ANLS on DocVQA, and 88.1% accuracy@0.5 on RefCOCOg-test.		None
Historical Ink: 19th Century Latin American Spanish Newspaper Corpus with LLM OCR Correction	2024-10-04	Show This paper presents two significant contributions: First, it introduces a novel dataset of 19th-century Latin American newspaper texts, addressing a critical gap in specialized corpora for historical and linguistic analysis in this region. Second, it develops a flexible framework that utilizes a Large Language Model for OCR error correction and linguistic surface form detection in digitized corpora. This semi-automated framework is adaptable to various contexts and datasets and is applied to the newly created dataset.		None
JaPOC: Japanese Post-OCR Correction Benchmark using Vouchers	2024-09-30	Show In this paper, we create benchmarks and assess the effectiveness of error correction methods for Japanese vouchers in OCR (Optical Character Recognition) systems. It is essential for automation processing to correctly recognize scanned voucher text, such as the company name on invoices. However, perfect recognition is complex due to the noise, such as stamps. Therefore, it is crucial to correctly rectify erroneous OCR results. However, no publicly available OCR error correction benchmarks for Japanese exist, and methods have not been adequately researched. In this study, we measured text recognition accuracy by existing services on Japanese vouchers and developed a post-OCR correction benchmark. Then, we proposed simple baselines for error correction using language models and verified whether the proposed method could effectively correct these errors. In the experiments, the proposed error correction algorithm significantly improved overall recognition accuracy.	Accep... Accepted to PRICAI 2024	None
Scrambled text: training Language Models to correct OCR errors using synthetic data	2024-09-29	Show OCR errors are common in digitised historical archives significantly affecting their usability and value. Generative Language Models (LMs) have shown potential for correcting these errors using the context provided by the corrupted text and the broader socio-cultural context, a process called Context Leveraging OCR Correction (CLOCR-C). However, getting sufficient training data for fine-tuning such models can prove challenging. This paper shows that fine-tuning a language model on synthetic data using an LM and using a character level Markov corruption process can significantly improve the ability to correct OCR errors. Models trained on synthetic data reduce the character error rate by 55% and word error rate by 32% over the base LM and outperform models trained on real data. Key findings include; training on under-corrupted data is better than over-corrupted data; non-uniform character level corruption is better than uniform corruption; More tokens-per-observation outperforms more observations for a fixed token budget. The outputs for this paper are a set of 8 heuristics for training effective CLOCR-C models, a dataset of 11,000 synthetic 19th century newspaper articles and scrambledtext a python library for creating synthetic corrupted data.	21 pa... 21 pages, 6300 words, 6 Figures, 5 tables	None
MaViLS, a Benchmark Dataset for Video-to-Slide Alignment, Assessing Baseline Accuracy with a Multimodal Alignment Algorithm Leveraging Speech, OCR, and Visual Features	2024-09-25	Show This paper presents a benchmark dataset for aligning lecture videos with corresponding slides and introduces a novel multimodal algorithm leveraging features from speech, text, and images. It achieves an average accuracy of 0.82 in comparison to SIFT (0.56) while being approximately 11 times faster. Using dynamic programming the algorithm tries to determine the optimal slide sequence. The results show that penalizing slide transitions increases accuracy. Features obtained via optical character recognition (OCR) contribute the most to a high matching accuracy, followed by image features. The findings highlight that audio transcripts alone provide valuable information for alignment and are beneficial if OCR data is lacking. Variations in matching accuracy across different lectures highlight the challenges associated with video quality and lecture style. The novel multimodal algorithm demonstrates robustness to some of these challenges, underscoring the potential of the approach.		None
Computer Vision Intelligence Test Modeling and Generation: A Case Study on Smart OCR	2024-09-14	Show AI-based systems possess distinctive characteristics and introduce challenges in quality evaluation at the same time. Consequently, ensuring and validating AI software quality is of critical importance. In this paper, we present an effective AI software functional testing model to address this challenge. Specifically, we first present a comprehensive literature review of previous work, covering key facets of AI software testing processes. We then introduce a 3D classification model to systematically evaluate the image-based text extraction AI function, as well as test coverage criteria and complexity. To evaluate the performance of our proposed AI software quality test, we propose four evaluation metrics to cover different aspects. Finally, based on the proposed framework and defined metrics, a mobile Optical Character Recognition (OCR) case study is presented to demonstrate the framework's effectiveness and capability in assessing AI function quality.		None
mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding	2024-09-09	Show Multimodel Large Language Models(MLLMs) have achieved promising OCR-free Document Understanding performance by increasing the supported resolution of document images. However, this comes at the cost of generating thousands of visual tokens for a single document image, leading to excessive GPU memory and slower inference times, particularly in multi-page document comprehension. In this work, to address these challenges, we propose a High-resolution DocCompressor module to compress each high-resolution document image into 324 tokens, guided by low-resolution global visual features. With this compression module, to strengthen multi-page document comprehension ability and balance both token efficiency and question-answering performance, we develop the DocOwl2 under a three-stage training framework: Single-image Pretraining, Multi-image Continue-pretraining, and Multi-task Finetuning. DocOwl2 sets a new state-of-the-art across multi-page document understanding benchmarks and reduces first token latency by more than 50%, demonstrating advanced capabilities in multi-page questioning answering, explanation with evidence pages, and cross-page structure understanding. Additionally, compared to single-image MLLMs trained on similar data, our DocOwl2 achieves comparable single-page understanding performance with less than 20% of the visual tokens. Our codes, models, and data are publicly available at https://github.com/X-PLUG/mPLUG-DocOwl/tree/main/DocOwl2.	15 pages, 7 figures	Code Link
Confidence-Aware Document OCR Error Detection	2024-09-06	Show Optical Character Recognition (OCR) continues to face accuracy challenges that impact subsequent applications. To address these errors, we explore the utility of OCR confidence scores for enhancing post-OCR error detection. Our study involves analyzing the correlation between confidence scores and error rates across different OCR systems. We develop ConfBERT, a BERT-based model that incorporates OCR confidence scores into token embeddings and offers an optional pre-training phase for noise adjustment. Our experimental results demonstrate that integrating OCR confidence scores can enhance error detection capabilities. This work underscores the importance of OCR confidence scores in improving detection accuracy and reveals substantial disparities in performance between commercial and open-source OCR technologies.		None
General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model	2024-09-03	Show Traditional OCR systems (OCR-1.0) are increasingly unable to meet people's usage due to the growing demand for intelligent processing of man-made optical characters. In this paper, we collectively refer to all artificial optical signals (e.g., plain texts, math/molecular formulas, tables, charts, sheet music, and even geometric shapes) as "characters" and propose the General OCR Theory along with an excellent model, namely GOT, to promote the arrival of OCR-2.0. The GOT, with 580M parameters, is a unified, elegant, and end-to-end model, consisting of a high-compression encoder and a long-contexts decoder. As an OCR-2.0 model, GOT can handle all the above "characters" under various OCR tasks. On the input side, the model supports commonly used scene- and document-style images in slice and whole-page styles. On the output side, GOT can generate plain or formatted results (markdown/tikz/smiles/kern) via an easy prompt. Besides, the model enjoys interactive OCR features, i.e., region-level recognition guided by coordinates or colors. Furthermore, we also adapt dynamic resolution and multi-page OCR technologies to GOT for better practicality. In experiments, we provide sufficient results to prove the superiority of our model.		None
Post-OCR Text Correction for Bulgarian Historical Documents	2024-08-31	Show The digitization of historical documents is crucial for preserving the cultural heritage of the society. An important step in this process is converting scanned images to text using Optical Character Recognition (OCR), which can enable further search, information extraction, etc. Unfortunately, this is a hard problem as standard OCR tools are not tailored to deal with historical orthography as well as with challenging layouts. Thus, it is standard to apply an additional text correction step on the OCR output when dealing with such documents. In this work, we focus on Bulgarian, and we create the first benchmark dataset for evaluating the OCR text correction for historical Bulgarian documents written in the first standardized Bulgarian orthography: the Drinov orthography from the 19th century. We further develop a method for automatically generating synthetic data in this orthography, as well as in the subsequent Ivanchev orthography, by leveraging vast amounts of contemporary literature Bulgarian texts. We then use state-of-the-art LLMs and encoder-decoder framework which we augment with diagonal attention loss and copy and coverage mechanisms to improve the post-OCR text correction. The proposed method reduces the errors introduced during recognition and improves the quality of the documents by 25%, which is an increase of 16% compared to the state-of-the-art on the ICDAR 2019 Bulgarian dataset. We release our data and code at \url{https://github.com/angelbeshirov/post-ocr-text-correction}.}	Accep... Accepted for publication in the International Journal on Digital Libraries	Code Link
Can Visual Language Models Replace OCR-Based Visual Question Answering Pipelines in Production? A Case Study in Retail	2024-08-28	Show Most production-level deployments for Visual Question Answering (VQA) tasks are still build as processing pipelines of independent steps including image pre-processing, object- and text detection, Optical Character Recognition (OCR) and (mostly supervised) object classification. However, the recent advances in vision Foundation Models [25] and Vision Language Models (VLMs) [23] raise the question if these custom trained, multi-step approaches can be replaced with pre-trained, single-step VLMs. This paper analyzes the performance and limits of various VLMs in the context of VQA and OCR [5, 9, 12] tasks in a production-level scenario. Using data from the Retail-786k [10] dataset, we investigate the capabilities of pre-trained VLMs to answer detailed questions about advertised products in images. Our study includes two commercial models, GPT-4V [16] and GPT-4o [17], as well as four open-source models: InternVL [5], LLaVA 1.5 [12], LLaVA-NeXT [13], and CogAgent [9]. Our initial results show, that there is in general no big performance gap between open-source and commercial models. However, we observe a strong task dependent variance in VLM performance: while most models are able to answer questions regarding the product brand and price with high accuracy, they completely fail at the same time to correctly identity the specific product name or discount. This indicates the problem of VLMs to solve fine-grained classification tasks as well to model the more abstract concept of discounts.		None
OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models	2024-08-26	Show Large models have recently played a dominant role in natural language processing and multimodal vision-language learning. However, their effectiveness in text-related visual tasks remains relatively unexplored. In this paper, we conducted a comprehensive evaluation of Large Multimodal Models, such as GPT4V and Gemini, in various text-related visual tasks including Text Recognition, Scene Text-Centric Visual Question Answering (VQA), Document-Oriented VQA, Key Information Extraction (KIE), and Handwritten Mathematical Expression Recognition (HMER). To facilitate the assessment of Optical Character Recognition (OCR) capabilities in Large Multimodal Models, we propose OCRBench, a comprehensive evaluation benchmark. OCRBench contains 29 datasets, making it the most comprehensive OCR evaluation benchmark available. Furthermore, our study reveals both the strengths and weaknesses of these models, particularly in handling multilingual text, handwritten text, non-semantic text, and mathematical expression recognition. Most importantly, the baseline results presented in this study could provide a foundational framework for the conception and assessment of innovative strategies targeted at enhancing zero-shot multimodal techniques. The evaluation pipeline and benchmark are available at https://github.com/Yuliang-Liu/MultimodalOCR.		Code Link
Advancing Post-OCR Correction: A Comparative Study of Synthetic Data	2024-08-13	Show This paper explores the application of synthetic data in the post-OCR domain on multiple fronts by conducting experiments to assess the impact of data volume, augmentation, and synthetic data generation methods on model performance. Furthermore, we introduce a novel algorithm that leverages computer vision feature detection algorithms to calculate glyph similarity for constructing post-OCR synthetic data. Through experiments conducted across a variety of languages, including several low-resource ones, we demonstrate that models like ByT5 can significantly reduce Character Error Rates (CER) without the need for manually annotated data, and our proposed synthetic data generation method shows advantages over traditional methods, particularly in low-resource languages.	ACL 2024 findings	None
Efficient OCR for Building a Diverse Digital History	2024-07-25	Show Thousands of users consult digital archives daily, but the information they can access is unrepresentative of the diversity of documentary history. The sequence-to-sequence architecture typically used for optical character recognition (OCR) - which jointly learns a vision and language model - is poorly extensible to low-resource document collections, as learning a language-vision model requires extensive labeled sequences and compute. This study models OCR as a character level image retrieval problem, using a contrastively trained vision encoder. Because the model only learns characters' visual features, it is more sample efficient and extensible than existing architectures, enabling accurate OCR in settings where existing solutions fail. Crucially, the model opens new avenues for community engagement in making digital history more representative of documentary history.		None
DocParseNet: Advanced Semantic Segmentation and OCR Embeddings for Efficient Scanned Document Annotation	2024-07-21	Show Automating the annotation of scanned documents is challenging, requiring a balance between computational efficiency and accuracy. DocParseNet addresses this by combining deep learning and multi-modal learning to process both text and visual data. This model goes beyond traditional OCR and semantic segmentation, capturing the interplay between text and images to preserve contextual nuances in complex document structures. Our evaluations show that DocParseNet significantly outperforms conventional models, achieving mIoU scores of 49.12 on validation and 49.78 on the test set. This reflects a 58% accuracy improvement over state-of-the-art baseline models and an 18% gain compared to the UNext baseline. Remarkably, DocParseNet achieves these results with only 2.8 million parameters, reducing the model size by approximately 25 times and speeding up training by 5 times compared to other models. These metrics, coupled with a computational efficiency of 0.039 TFLOPs (BS=1), highlight DocParseNet's high performance in document annotation. The model's adaptability and scalability make it well-suited for real-world corporate document processing applications. The code is available at https://github.com/ahmad-shirazi/DocParseNet		Code Link
Optimizing Nepali PDF Extraction: A Comparative Study of Parser and OCR Technologies	2024-07-09	Show This research compares PDF parsing and Optical Character Recognition (OCR) methods for extracting Nepali content from PDFs. PDF parsing offers fast and accurate extraction but faces challenges with non-Unicode Nepali fonts. OCR, specifically PyTesseract, overcomes these challenges, providing versatility for both digital and scanned PDFs. The study reveals that while PDF parsers are faster, their accuracy fluctuates based on PDF types. In contrast, OCRs, with a focus on PyTesseract, demonstrate consistent accuracy at the expense of slightly longer extraction times. Considering the project's emphasis on Nepali PDFs, PyTesseract emerges as the most suitable library, balancing extraction speed and accuracy.		None
CORU: Comprehensive Post-OCR Parsing and Receipt Understanding Dataset	2024-06-06	Show In the fields of Optical Character Recognition (OCR) and Natural Language Processing (NLP), integrating multilingual capabilities remains a critical challenge, especially when considering languages with complex scripts such as Arabic. This paper introduces the Comprehensive Post-OCR Parsing and Receipt Understanding Dataset (CORU), a novel dataset specifically designed to enhance OCR and information extraction from receipts in multilingual contexts involving Arabic and English. CORU consists of over 20,000 annotated receipts from diverse retail settings, including supermarkets and clothing stores, alongside 30,000 annotated images for OCR that were utilized to recognize each detected line, and 10,000 items annotated for detailed information extraction. These annotations capture essential details such as merchant names, item descriptions, total prices, receipt numbers, and dates. They are structured to support three primary computational tasks: object detection, OCR, and information extraction. We establish the baseline performance for a range of models on CORU to evaluate the effectiveness of traditional methods, like Tesseract OCR, and more advanced neural network-based approaches. These baselines are crucial for processing the complex and noisy document layouts typical of real-world receipts and for advancing the state of automated multilingual document processing. Our datasets are publicly accessible (https://github.com/Update-For-Integrated-Business-AI/CORU).		Code Link
Cleansing Jewel: A Neural Spelling Correction Model Built On Google OCR-ed Tibetan Manuscripts	2024-05-14	Show Scholars in the humanities rely heavily on ancient manuscripts to study history, religion, and socio-political structures in the past. Many efforts have been devoted to digitizing these precious manuscripts using OCR technology, but most manuscripts were blemished over the centuries so that an Optical Character Recognition (OCR) program cannot be expected to capture faded graphs and stains on pages. This work presents a neural spelling correction model built on Google OCR-ed Tibetan Manuscripts to auto-correct OCR-ed noisy output. This paper is divided into four sections: dataset, model architecture, training and analysis. First, we feature-engineered our raw Tibetan etext corpus into two sets of structured data frames -- a set of paired toy data and a set of paired real data. Then, we implemented a Confidence Score mechanism into the Transformer architecture to perform spelling correction tasks. According to the Loss and Character Error Rate, our Transformer + Confidence score mechanism architecture proves to be superior to Transformer, LSTM-2-LSTM and GRU-2-GRU architectures. Finally, to examine the robustness of our model, we analyzed erroneous tokens, visualized Attention and Self-Attention heatmaps in our model.		None
TC-OCR: TableCraft OCR for Efficient Detection & Recognition of Table Structure & Content	2024-04-19	Show The automatic recognition of tabular data in document images presents a significant challenge due to the diverse range of table styles and complex structures. Tables offer valuable content representation, enhancing the predictive capabilities of various systems such as search engines and Knowledge Graphs. Addressing the two main problems, namely table detection (TD) and table structure recognition (TSR), has traditionally been approached independently. In this research, we propose an end-to-end pipeline that integrates deep learning models, including DETR, CascadeTabNet, and PP OCR v2, to achieve comprehensive image-based table recognition. This integrated approach effectively handles diverse table styles, complex structures, and image distortions, resulting in improved accuracy and efficiency compared to existing methods like Table Transformers. Our system achieves simultaneous table detection (TD), table structure recognition (TSR), and table content recognition (TCR), preserving table structures and accurately extracting tabular data from document images. The integration of multiple models addresses the intricacies of table recognition, making our approach a promising solution for image-based table understanding, data extraction, and information retrieval applications. Our proposed approach achieves an IOU of 0.96 and an OCR Accuracy of 78%, showcasing a remarkable improvement of approximately 25% in the OCR Accuracy compared to the previous Table Transformer approach.	8 pag... 8 pages, 2 figures, Workshop of 1st MMIR Deep Multimodal Learning for Information Retrieval	None
OCR is All you need: Importing Multi-Modality into Image-based Defect Detection System	2024-03-18	Show Automatic optical inspection (AOI) plays a pivotal role in the manufacturing process, predominantly leveraging high-resolution imaging instruments for scanning purposes. It detects anomalies by analyzing image textures or patterns, making it an essential tool in industrial manufacturing and quality control. Despite its importance, the deployment of models for AOI often faces challenges. These include limited sample sizes, which hinder effective feature learning, variations among source domains, and sensitivities to changes in lighting and camera positions during imaging. These factors collectively compromise the accuracy of model predictions. Traditional AOI often fails to capitalize on the rich mechanism-parameter information from machines or inside images, including statistical parameters, which typically benefit AOI classification. To address this, we introduce an external modality-guided data mining framework, primarily rooted in optical character recognition (OCR), to extract statistical features from images as a second modality to enhance performance, termed OANet (Ocr-Aoi-Net). A key aspect of our approach is the alignment of external modality features, extracted using a single modality-aware model, with image features encoded by a convolutional neural network. This synergy enables a more refined fusion of semantic representations from different modalities. We further introduce feature refinement and a gating function in our OANet to optimize the combination of these features, enhancing inference and decision-making capabilities. Experimental outcomes show that our methodology considerably boosts the recall rate of the defect detection model and maintains high robustness even in challenging scenarios.		None
TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document	2024-03-15	Show We present TextMonkey, a large multimodal model (LMM) tailored for text-centric tasks. Our approach introduces enhancement across several dimensions: By adopting Shifted Window Attention with zero-initialization, we achieve cross-window connectivity at higher input resolutions and stabilize early training; We hypothesize that images may contain redundant tokens, and by using similarity to filter out significant tokens, we can not only streamline the token length but also enhance the model's performance. Moreover, by expanding our model's capabilities to encompass text spotting and grounding, and incorporating positional information into responses, we enhance interpretability. It also learns to perform screenshot tasks through finetuning. Evaluation on 12 benchmarks shows notable improvements: 5.2% in Scene Text-Centric tasks (including STVQA, TextVQA, and OCRVQA), 6.9% in Document-Oriented tasks (such as DocVQA, InfoVQA, ChartVQA, DeepForm, Kleister Charity, and WikiTableQuestions), and 2.8% in Key Information Extraction tasks (comprising FUNSD, SROIE, and POIE). It outperforms in scene text spotting with a 10.9% increase and sets a new standard on OCRBench, a comprehensive benchmark consisting of 29 OCR-related assessments, with a score of 561, surpassing previous open-sourced large multimodal models for document understanding. Code will be released at https://github.com/Yuliang-Liu/Monkey.		Code Link
Adversarial Training with OCR Modality Perturbation for Scene-Text Visual Question Answering	2024-03-14	Show Scene-Text Visual Question Answering (ST-VQA) aims to understand scene text in images and answer questions related to the text content. Most existing methods heavily rely on the accuracy of Optical Character Recognition (OCR) systems, and aggressive fine-tuning based on limited spatial location information and erroneous OCR text information often leads to inevitable overfitting. In this paper, we propose a multimodal adversarial training architecture with spatial awareness capabilities. Specifically, we introduce an Adversarial OCR Enhancement (AOE) module, which leverages adversarial training in the embedding space of OCR modality to enhance fault-tolerant representation of OCR texts, thereby reducing noise caused by OCR errors. Simultaneously, We add a Spatial-Aware Self-Attention (SASA) mechanism to help the model better capture the spatial relationships among OCR tokens. Various experiments demonstrate that our method achieves significant performance improvements on both the ST-VQA and TextVQA datasets and provides a novel paradigm for multimodal adversarial training.	6 pag... 6 pages, 3 figures, accepted by 2024 IEEE International Conference on Multimedia and Expo	None
Advancing Generative Model Evaluation: A Novel Algorithm for Realistic Image Synthesis and Comparison in OCR System	2024-03-01	Show This research addresses a critical challenge in the field of generative models, particularly in the generation and evaluation of synthetic images. Given the inherent complexity of generative models and the absence of a standardized procedure for their comparison, our study introduces a pioneering algorithm to objectively assess the realism of synthetic images. This approach significantly enhances the evaluation methodology by refining the Fr'echet Inception Distance (FID) score, allowing for a more precise and subjective assessment of image quality. Our algorithm is particularly tailored to address the challenges in generating and evaluating realistic images of Arabic handwritten digits, a task that has traditionally been near-impossible due to the subjective nature of realism in image generation. By providing a systematic and objective framework, our method not only enables the comparison of different generative models but also paves the way for improvements in their design and output. This breakthrough in evaluation and comparison is crucial for advancing the field of OCR, especially for scripts that present unique complexities, and sets a new standard in the generation and assessment of high-quality synthetic images.	The m... The manuscript was submitted to IEEE Access on 29-Jan-2024 and is currently under review for publication in IEEE Access	None
Advances and Limitations in Open Source Arabic-Script OCR: A Case Study	2024-02-08	Show This work presents an accuracy study of the open source OCR engine, Kraken, on the leading Arabic scholarly journal, al-Abhath. In contrast with other commercially available OCR engines, Kraken is shown to be capable of producing highly accurate Arabic-script OCR. The study also assesses the relative accuracy of typeface-specific and generalized models on the al-Abhath data and provides a microanalysis of the ``error instances'' and the contextual features that may have contributed to OCR misrecognition. Building on this analysis, the paper argues that Arabic-script OCR can be significantly improved through (1) a more systematic approach to training data production, and (2) the development of key technological components, especially multi-language models and improved line segmentation and layout analysis. Cet article pr{'e}sente une {'e}tude d'exactitude du moteur ROC open source, Krakan, sur la revue acad{'e}mique arabe de premier rang, al-Abhath. Contrairement {`a} d'autres moteurs ROC disponibles sur le march{'e}, Kraken se r{'e}v{`e}le {^e}tre capable de produire de la ROC extr{^e}mement exacte de l'{'e}criture arabe. L'{'e}tude {'e}value aussi l'exactitude relative des mod{`e}les sp{'e}cifiquement configur{'e}s {`a} des polices et celle des mod{`e}les g{'e}n{'e}ralis{'e}s sur les donn{'e}es d'al-Abhath et fournit une microanalyse des "occurrences d'erreurs", ainsi qu'une microanalyse des {'e}l{'e}ments contextuels qui pourraient avoir contribu{'e} {`a} la m{'e}reconnaissance ROC. S'appuyant sur cette analyse, cet article fait valoir que la ROC de l'{'e}criture arabe peut {^e}tre consid{'e}rablement am{'e}lior{'e}e gr{^a}ce {`a} (1) une approche plus syst{'e}matique d'entra{^i}nement de la production de donn{'e}es et (2) gr{^a}ce au d{'e}veloppement de composants technologiques fondamentaux, notammentl'am{'e}lioration des mod{`e}les multilingues, de la segmentation de ligne et de l'analyse de la mise en page.		None
Segmentation-free Connectionist Temporal Classification loss based OCR Model for Text Captcha Classification	2024-02-08	Show Captcha are widely used to secure systems from automatic responses by distinguishing computer responses from human responses. Text, audio, video, picture picture-based Optical Character Recognition (OCR) are used for creating captcha. Text-based OCR captcha are the most often used captcha which faces issues namely, complex and distorted contents. There are attempts to build captcha detection and classification-based systems using machine learning and neural networks, which need to be tuned for accuracy. The existing systems face challenges in the recognition of distorted characters, handling variable-length captcha and finding sequential dependencies in captcha. In this work, we propose a segmentation-free OCR model for text captcha classification based on the connectionist temporal classification loss technique. The proposed model is trained and tested on a publicly available captcha dataset. The proposed model gives 99.80% character level accuracy, while 95% word level accuracy. The accuracy of the proposed model is compared with the state-of-the-art models and proves to be effective. The variable length complex captcha can be thus processed with the segmentation-free connectionist temporal classification loss technique with dependencies which will be massively used in securing the software systems.	17 pages, 5 figures	None
Enhancement of Bengali OCR by Specialized Models and Advanced Techniques for Diverse Document Types	2024-02-07	Show This research paper presents a unique Bengali OCR system with some capabilities. The system excels in reconstructing document layouts while preserving structure, alignment, and images. It incorporates advanced image and signature detection for accurate extraction. Specialized models for word segmentation cater to diverse document types, including computer-composed, letterpress, typewriter, and handwritten documents. The system handles static and dynamic handwritten inputs, recognizing various writing styles. Furthermore, it has the ability to recognize compound characters in Bengali. Extensive data collection efforts provide a diverse corpus, while advanced technical components optimize character and word recognition. Additional contributions include image, logo, signature and table recognition, perspective correction, layout reconstruction, and a queuing module for efficient and scalable processing. The system demonstrates outstanding performance in efficient and accurate text extraction and analysis.	8 pag... 8 pages, 7 figures, 4 table Link of the paper https://openaccess.thecvf.com/content/WACV2024W/WVLL/html/Rabby_Enhancement_of_Bengali_OCR_by_Specialized_Models_and_Advanced_Techniques_WACVW_2024_paper.html	None
An Empirical Study of Scaling Law for OCR	2024-01-31	Show The laws of model size, data volume, computation and model performance have been extensively studied in the field of Natural Language Processing (NLP). However, the scaling laws in Optical Character Recognition (OCR) have not yet been investigated. To address this, we conducted comprehensive studies that involved examining the correlation between performance and the scale of models, data volume and computation in the field of text recognition.Conclusively, the study demonstrates smooth power laws between performance and model size, as well as training data volume, when other influencing factors are held constant. Additionally, we have constructed a large-scale dataset called REBU-Syn, which comprises 6 million real samples and 18 million synthetic samples. Based on our scaling law and new dataset, we have successfully trained a scene text recognition model, achieving a new state-ofthe-art on 6 common test benchmarks with a top-1 average accuracy of 97.42%. The models and dataset are publicly available at https://github.com/large-ocr-model/large-ocr-model.github.io.		Code Link
Improving OCR Quality in 19th Century Historical Documents Using a Combined Machine Learning Based Approach	2024-01-15	Show This paper addresses a major challenge to historical research on the 19th century. Large quantities of sources have become digitally available for the first time, while extraction techniques are lagging behind. Therefore, we researched machine learning (ML) models to recognise and extract complex data structures in a high-value historical primary source, the Schematismus. It records every single person in the Habsburg civil service above a certain hierarchical level between 1702 and 1918 and documents the genesis of the central administration over two centuries. Its complex and intricate structure as well as its enormous size have so far made any more comprehensive analysis of the administrative and social structure of the later Habsburg Empire on the basis of this source impossible. We pursued two central objectives: Primarily, the improvement of the OCR quality, for which we considered an improved structure recognition to be essential; in the further course, it turned out that this also made the extraction of the data structure possible. We chose Faster R-CNN as base for the ML architecture for structure recognition. In order to obtain the required amount of training data quickly and economically, we synthesised Hof- und Staatsschematismus-style data, which we used to train our model. The model was then fine-tuned with a smaller set of manually annotated historical source data. We then used Tesseract-OCR, which was further optimised for the style of our documents, to complete the combined structure extraction and OCR process. Results show a significant decrease in the two standard parameters of OCR-performance, WER and CER (where lower values are better). Combined structure detection and fine-tuned OCR improved CER and WER values by remarkable 71.98 percent (CER) respectively 52.49 percent (WER).	29 pa... 29 pages, 23 figures, 7 tables	None
UPOCR: Towards Unified Pixel-Level OCR Interface	2023-12-05	Show In recent years, the optical character recognition (OCR) field has been proliferating with plentiful cutting-edge approaches for a wide spectrum of tasks. However, these approaches are task-specifically designed with divergent paradigms, architectures, and training strategies, which significantly increases the complexity of research and maintenance and hinders the fast deployment in applications. To this end, we propose UPOCR, a simple-yet-effective generalist model for Unified Pixel-level OCR interface. Specifically, the UPOCR unifies the paradigm of diverse OCR tasks as image-to-image transformation and the architecture as a vision Transformer (ViT)-based encoder-decoder. Learnable task prompts are introduced to push the general feature representations extracted by the encoder toward task-specific spaces, endowing the decoder with task awareness. Moreover, the model training is uniformly aimed at minimizing the discrepancy between the generated and ground-truth images regardless of the inhomogeneity among tasks. Experiments are conducted on three pixel-level OCR tasks including text removal, text segmentation, and tampered text detection. Without bells and whistles, the experimental results showcase that the proposed method can simultaneously achieve state-of-the-art performance on three tasks with a unified single model, which provides valuable strategies and insights for future research on generalist OCR models. Code will be publicly available.		None
Data Generation for Post-OCR correction of Cyrillic handwriting	2023-11-27	Show This paper introduces a novel approach to post-Optical Character Recognition Correction (POC) for handwritten Cyrillic text, addressing a significant gap in current research methodologies. This gap is due to the lack of large text corporas that provide OCR errors for further training of language-based POC models, which are demanding in terms of corpora size. Our study primarily focuses on the development and application of a synthetic handwriting generation engine based on B'ezier curves. Such an engine generates highly realistic handwritten text in any amounts, which we utilize to create a substantial dataset by transforming Russian text corpora sourced from the internet. We apply a Handwritten Text Recognition (HTR) model to this dataset to identify OCR errors, forming the basis for our POC model training. The correction model is trained on a 90-symbol input context, utilizing a pre-trained T5 architecture with a seq2seq correction task. We evaluate our approach on HWR200 and School_notebooks_RU datasets as they provide significant challenges in the HTR domain. Furthermore, POC can be used to highlight errors for teachers, evaluating student performance. This can be done simply by comparing sentences before and after correction, displaying differences in text. Our primary contribution lies in the innovative use of B'ezier curves for Cyrillic text generation and subsequent error correction using a specialized POC model. We validate our approach by presenting Word Accuracy Rate (WAR) and Character Accuracy Rate (CAR) results, both with and without post-OCR correction, using real open corporas of handwritten Cyrillic text. These results, coupled with our methodology, are designed to be reproducible, paving the way for further advancements in the field of OCR and handwritten text analysis. Paper contributions can be found in https://github.com/dbrainio/CyrillicHandwritingPOC	17 pa... 17 pages, 27 figures, 6 tables, 26 references	Code Link
Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation	2023-10-29	Show This paper presents a comprehensive evaluation of the Optical Character Recognition (OCR) capabilities of the recently released GPT-4V(ision), a Large Multimodal Model (LMM). We assess the model's performance across a range of OCR tasks, including scene text recognition, handwritten text recognition, handwritten mathematical expression recognition, table structure recognition, and information extraction from visually-rich document. The evaluation reveals that GPT-4V performs well in recognizing and understanding Latin contents, but struggles with multilingual scenarios and complex tasks. Specifically, it showed limitations when dealing with non-Latin languages and complex tasks such as handwriting mathematical expression recognition, table structure recognition, and end-to-end semantic entity recognition and pair extraction from document image. Based on these observations, we affirm the necessity and continued research value of specialized OCR models. In general, despite its versatility in handling diverse OCR tasks, GPT-4V does not outperform existing state-of-the-art OCR models. How to fully utilize pre-trained general-purpose LMMs such as GPT-4V for OCR downstream tasks remains an open problem. The study offers a critical reference for future research in OCR with LMMs. Evaluation pipeline and results are available at https://github.com/SCUT-DLVCLab/GPT-4V_OCR.		Code Link
Extending TrOCR for Text Localization-Free OCR of Full-Page Scanned Receipt Images	2023-10-16	Show Digitization of scanned receipts aims to extract text from receipt images and save it into structured documents. This is usually split into two sub-tasks: text localization and optical character recognition (OCR). Most existing OCR models only focus on the cropped text instance images, which require the bounding box information provided by a text region detection model. Introducing an additional detector to identify the text instance images in advance adds complexity, however instance-level OCR models have very low accuracy when processing the whole image for the document-level OCR, such as receipt images containing multiple text lines arranged in various layouts. To this end, we propose a localization-free document-level OCR model for transcribing all the characters in a receipt image into an ordered sequence end-to-end. Specifically, we finetune the pretrained instance-level model TrOCR with randomly cropped image chunks, and gradually increase the image chunk size to generalize the recognition ability from instance images to full-page images. In our experiments on the SROIE receipt OCR dataset, the model finetuned with our strategy achieved 64.4 F1-score and a 22.8% character error rate (CER), respectively, which outperforms the baseline results with 48.5 F1-score and 50.6% CER. The best model, which splits the full image into 15 equally sized chunks, gives 87.8 F1-score and 4.98% CER with minimal additional pre or post-processing of the output. Moreover, the characters in the generated document-level sequences are arranged in the reading order, which is practical for real-world applications.	ICCV2... ICCV2023 RCV Workshop	None
Invisible Threats: Backdoor Attack in OCR Systems	2023-10-12	Show Optical Character Recognition (OCR) is a widely used tool to extract text from scanned documents. Today, the state-of-the-art is achieved by exploiting deep neural networks. However, the cost of this performance is paid at the price of system vulnerability. For instance, in backdoor attacks, attackers compromise the training phase by inserting a backdoor in the victim's model that will be activated at testing time by specific patterns while leaving the overall model performance intact. This work proposes a backdoor attack for OCR resulting in the injection of non-readable characters from malicious input images. This simple but effective attack exposes the state-of-the-art OCR weakness, making the extracted text correct to human eyes but simultaneously unusable for the NLP application that uses OCR as a preprocessing step. Experimental results show that the attacked models successfully output non-readable characters for around 90% of the poisoned instances without harming their performance for the remaining instances.		None
UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model	2023-10-08	Show Text is ubiquitous in our visual world, conveying crucial information, such as in documents, websites, and everyday photographs. In this work, we propose UReader, a first exploration of universal OCR-free visually-situated language understanding based on the Multimodal Large Language Model (MLLM). By leveraging the shallow text recognition ability of the MLLM, we only finetuned 1.2% parameters and the training cost is much lower than previous work following domain-specific pretraining and finetuning paradigms. Concretely, UReader is jointly finetuned on a wide range of Visually-situated Language Understanding tasks via a unified instruction format. To enhance the visual text and semantic understanding, we further apply two auxiliary tasks with the same format, namely text reading and key points generation tasks. We design a shape-adaptive cropping module before the encoder-decoder architecture of MLLM to leverage the frozen low-resolution vision encoder for processing high-resolution images. Without downstream finetuning, our single model achieves state-of-the-art ocr-free performance in 8 out of 10 visually-situated language understanding tasks, across 5 domains: documents, tables, charts, natural images, and webpage screenshots. Codes and instruction-tuning datasets will be released.		None
Large Synthetic Data from the arXiv for OCR Post Correction of Historic Scientific Articles	2023-09-20	Show Scientific articles published prior to the "age of digitization" (~1997) require Optical Character Recognition (OCR) to transform scanned documents into machine-readable text, a process that often produces errors. We develop a pipeline for the generation of a synthetic ground truth/OCR dataset to correct the OCR results of the astrophysics literature holdings of the NASA Astrophysics Data System (ADS). By mining the arXiv we create, to the authors' knowledge, the largest scientific synthetic ground truth/OCR post correction dataset of 203,354,393 character pairs. We provide baseline models trained with this dataset and find the mean improvement in character and word error rates of 7.71% and 18.82% for historical OCR text, respectively. When used to classify parts of sentences as inline math, we find a classification F1 score of 77.82%. Interactive dashboards to explore the dataset are available online: https://readingtimemachine.github.io/projects/1-ocr-groundtruth-may2023, and data and code, within the limitations of our agreement with the arXiv, are hosted on GitHub: https://github.com/ReadingTimeMachine/ocr_post_correction.	6 pag... 6 pages, 1 figure, 1 table; training/validation/test datasets and all model weights to be linked on Zenodo on publication	Code Link
Enhancing OCR Performance through Post-OCR Models: Adopting Glyph Embedding for Improved Correction	2023-08-29	Show The study investigates the potential of post-OCR models to overcome limitations in OCR models and explores the impact of incorporating glyph embedding on post-OCR correction performance. In this study, we have developed our own post-OCR correction model. The novelty of our approach lies in embedding the OCR output using CharBERT and our unique embedding technique, capturing the visual characteristics of characters. Our findings show that post-OCR correction effectively addresses deficiencies in inferior OCR models, and glyph embedding enables the model to achieve superior results, including the ability to correct individual words.		None
DISGO: Automatic End-to-End Evaluation for Scene Text OCR	2023-08-25	Show This paper discusses the challenges of optical character recognition (OCR) on natural scenes, which is harder than OCR on documents due to the wild content and various image backgrounds. We propose to uniformly use word error rates (WER) as a new measurement for evaluating scene-text OCR, both end-to-end (e2e) performance and individual system component performances. Particularly for the e2e metric, we name it DISGO WER as it considers Deletion, Insertion, Substitution, and Grouping/Ordering errors. Finally we propose to utilize the concept of super blocks to automatically compute BLEU scores for e2e OCR machine translation. The small SCUT public test set is used to demonstrate WER performance by a modularized OCR system.	9 pages	None
bbOCR: An Open-source Multi-domain OCR Pipeline for Bengali Documents	2023-08-22	Show Despite the existence of numerous Optical Character Recognition (OCR) tools, the lack of comprehensive open-source systems hampers the progress of document digitization in various low-resource languages, including Bengali. Low-resource languages, especially those with an alphasyllabary writing system, suffer from the lack of large-scale datasets for various document OCR components such as word-level OCR, document layout extraction, and distortion correction; which are available as individual modules in high-resource languages. In this paper, we introduce Bengali$.$AI-BRACU-OCR (bbOCR): an open-source scalable document OCR system that can reconstruct Bengali documents into a structured searchable digitized format that leverages a novel Bengali text recognition model and two novel synthetic datasets. We present extensive component-level and system-level evaluation: both use a novel diversified evaluation dataset and comprehensive evaluation metrics. Our extensive evaluation suggests that our proposed solution is preferable over the current state-of-the-art Bengali OCR systems. The source codes and datasets are available here: https://bengaliai.github.io/bbocr.		Code Link
OCR Language Models with Custom Vocabularies	2023-08-18	Show Language models are useful adjuncts to optical models for producing accurate optical character recognition (OCR) results. One factor which limits the power of language models in this context is the existence of many specialized domains with language statistics very different from those implied by a general language model - think of checks, medical prescriptions, and many other specialized document classes. This paper introduces an algorithm for efficiently generating and attaching a domain specific word based language model at run time to a general language model in an OCR system. In order to best use this model the paper also introduces a modified CTC beam search decoder which effectively allows hypotheses to remain in contention based on possible future completion of vocabulary words. The result is a substantial reduction in word error rate in recognizing material from specialized domains.		None
Optimizing the Neural Network Training for OCR Error Correction of Historical Hebrew Texts	2023-07-30	Show Over the past few decades, large archives of paper-based documents such as books and newspapers have been digitized using Optical Character Recognition. This technology is error-prone, especially for historical documents. To correct OCR errors, post-processing algorithms have been proposed based on natural language analysis and machine learning techniques such as neural networks. Neural network's disadvantage is the vast amount of manually labeled data required for training, which is often unavailable. This paper proposes an innovative method for training a light-weight neural network for Hebrew OCR post-correction using significantly less manually created data. The main research goal is to develop a method for automatically generating language and task-specific training data to improve the neural network results for OCR post-correction, and to investigate which type of dataset is the most effective for OCR post-correction of historical documents. To this end, a series of experiments using several datasets was conducted. The evaluation corpus was based on Hebrew newspapers from the JPress project. An analysis of historical OCRed newspapers was done to learn common language and corpus-specific OCR errors. We found that training the network using the proposed method is more effective than using randomly generated errors. The results also show that the performance of the neural network for OCR post-correction strongly depends on the genre and area of the training data. Moreover, neural networks that were trained with the proposed method outperform other state-of-the-art neural networks for OCR post-correction and complex spellcheckers. These results may have practical implications for many digital humanities projects.		None
Toward a Period-Specific Optimized Neural Network for OCR Error Correction of Historical Hebrew Texts	2023-07-30	Show Over the past few decades, large archives of paper-based historical documents, such as books and newspapers, have been digitized using the Optical Character Recognition (OCR) technology. Unfortunately, this broadly used technology is error-prone, especially when an OCRed document was written hundreds of years ago. Neural networks have shown great success in solving various text processing tasks, including OCR post-correction. The main disadvantage of using neural networks for historical corpora is the lack of sufficiently large training datasets they require to learn from, especially for morphologically-rich languages like Hebrew. Moreover, it is not clear what are the optimal structure and values of hyperparameters (predefined parameters) of neural networks for OCR error correction in Hebrew due to its unique features. Furthermore, languages change across genres and periods. These changes may affect the accuracy of OCR post-correction neural network models. To overcome these challenges, we developed a new multi-phase method for generating artificial training datasets with OCR errors and hyperparameters optimization for building an effective neural network for OCR post-correction in Hebrew.		None
Estimating Post-OCR Denoising Complexity on Numerical Texts	2023-07-03	Show Post-OCR processing has significantly improved over the past few years. However, these have been primarily beneficial for texts consisting of natural, alphabetical words, as opposed to documents of numerical nature such as invoices, payslips, medical certificates, etc. To evaluate the OCR post-processing difficulty of these datasets, we propose a method to estimate the denoising complexity of a text and evaluate it on several datasets of varying nature, and show that texts of numerical nature have a significant disadvantage. We evaluate the estimated complexity ranking with respect to the error rates of modern-day denoising approaches to show the validity of our estimator.	Accep... Accepted for publication in the ACIIDS 2023 CCIS PROCEEDINGS	None
Improving Handwritten OCR with Training Samples Generated by Glyph Conditional Denoising Diffusion Probabilistic Model	2023-05-31	Show Constructing a highly accurate handwritten OCR system requires large amounts of representative training data, which is both time-consuming and expensive to collect. To mitigate the issue, we propose a denoising diffusion probabilistic model (DDPM) to generate training samples. This model conditions on a printed glyph image and creates mappings between printed characters and handwritten images, thus enabling the generation of photo-realistic handwritten samples with diverse styles and unseen text contents. However, the text contents in synthetic images are not always consistent with the glyph conditional images, leading to unreliable labels of synthetic samples. To address this issue, we further propose a progressive data filtering strategy to add those samples with a high confidence of correctness to the training set. Experimental results on IAM benchmark task show that OCR model trained with augmented DDPM-synthesized training samples can achieve about 45% relative word error rate reduction compared with the one trained on real data only.		None
Combining OCR Models for Reading Early Modern Printed Books	2023-05-11	Show In this paper, we investigate the usage of fine-grained font recognition on OCR for books printed from the 15th to the 18th century. We used a newly created dataset for OCR of early printed books for which fonts are labeled with bounding boxes. We know not only the font group used for each character, but the locations of font changes as well. In books of this period, we frequently find font group changes mid-line or even mid-word that indicate changes in language. We consider 8 different font groups present in our corpus and investigate 13 different subsets: the whole dataset and text lines with a single font, multiple fonts, Roman fonts, Gothic fonts, and each of the considered fonts, respectively. We show that OCR performance is strongly impacted by font style and that selecting fine-tuned models with font group recognition has a very positive impact on the results. Moreover, we developed a system using local font group recognition in order to combine the output of multiple font recognition models, and show that while slower, this approach performs better not only on text lines composed of multiple fonts but on the ones containing a single font only as well.	Accepted to ICDAR23	None
DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documents	2023-05-01	Show Information Extraction from visually rich documents is a challenging task that has gained a lot of attention in recent years due to its importance in several document-control based applications and its widespread commercial value. The majority of the research work conducted on this topic to date follow a two-step pipeline. First, they read the text using an off-the-shelf Optical Character Recognition (OCR) engine, then, they extract the fields of interest from the obtained text. The main drawback of these approaches is their dependence on an external OCR system, which can negatively impact both performance and computational speed. Recent OCR-free methods were proposed to address the previous issues. Inspired by their promising results, we propose in this paper an OCR-free end-to-end information extraction model named DocParser. It differs from prior end-to-end approaches by its ability to better extract discriminative character features. DocParser achieves state-of-the-art results on various datasets, while still being faster than previous works.	The 1... The 17th International Conference on Document Analysis and Recognition	None
User-Centric Evaluation of OCR Systems for Kwak'wala	2023-02-26	Show There has been recent interest in improving optical character recognition (OCR) for endangered languages, particularly because a large number of documents and books in these languages are not in machine-readable formats. The performance of OCR systems is typically evaluated using automatic metrics such as character and word error rates. While error rates are useful for the comparison of different models and systems, they do not measure whether and how the transcriptions produced from OCR tools are useful to downstream users. In this paper, we present a human-centric evaluation of OCR systems, focusing on the Kwak'wala language as a case study. With a user study, we show that utilizing OCR reduces the time spent in the manual transcription of culturally valuable documents -- a task that is often undertaken by endangered language community members and researchers -- by over 50%. Our results demonstrate the potential benefits that OCR tools can have on downstream language documentation and revitalization efforts.	Accep... Accepted to the Sixth Workshop on Computational Methods in the Study of Endangered Languages (ComputEL 2023)	None
TS-Net: OCR Trained to Switch Between Text Transcription Styles	2023-02-13	Show Users of OCR systems, from different institutions and scientific disciplines, prefer and produce different transcription styles. This presents a problem for training of consistent text recognition neural networks on real-world data. We propose to extend existing text recognition networks with a Transcription Style Block (TSB) which can learn from data to switch between multiple transcription styles without any explicit knowledge of transcription rules. TSB is an adaptive instance normalization conditioned by identifiers representing consistently transcribed documents (e.g. single document, documents by a single transcriber, or an institution). We show that TSB is able to learn completely different transcription styles in controlled experiments on artificial data, it improves text recognition accuracy on large-scale real-world data, and it learns semantically meaningful transcription style embedding. We also show how TSB can efficiently adapt to transcription styles of new documents from transcriptions of only a few text lines.		None
Text Detection Forgot About Document OCR	2023-01-23	Show Detection and recognition of text from scans and other images, commonly denoted as Optical Character Recognition (OCR), is a widely used form of automated document processing with a number of methods available. Yet OCR systems still do not achieve 100% accuracy, requiring human corrections in applications where correct readout is essential. Advances in machine learning enabled even more challenging scenarios of text detection and recognition "in-the-wild" - such as detecting text on objects from photographs of complex scenes. While the state-of-the-art methods for in-the-wild text recognition are typically evaluated on complex scenes, their performance in the domain of documents is typically not published, and a comprehensive comparison with methods for document OCR is missing. This paper compares several methods designed for in-the-wild text recognition and for document text recognition, and provides their evaluation on the domain of structured documents. The results suggest that state-of-the-art methods originally proposed for in-the-wild text detection also achieve competitive results on document text detection, outperforming available OCR methods. We argue that the application of document OCR should not be omitted in evaluation of text detection and recognition methods.	Accep... Accepted to the 26th Computer Vision Winter Workshop (CVWW), 2023	None
Adapting the Tesseract Open-Source OCR Engine for Tamil and Sinhala Legacy Fonts and Creating a Parallel Corpus for Tamil-Sinhala-English	2022-12-15	Show Most low-resource languages do not have the necessary resources to create even a substantial monolingual corpus. These languages may often be found in government proceedings but mainly in Portable Document Format (PDF) that contains legacy fonts. Extracting text from these documents to create a monolingual corpus is challenging due to legacy font usage and printer-friendly encoding, which are not optimized for text extraction. Therefore, we propose a simple, automatic, and novel idea that can scale for Tamil, Sinhala, English languages, and many documents along with parallel corpora. Since Tamil and Sinhala are Low-Resource Languages, we improved the performance of Tesseract by employing LSTM-based training on more than 20 legacy fonts to recognize printed characters in these languages. Especially, our model detects code-mixed text, numbers, and special characters from the printed document. It is shown that this approach can reduce the character-level error rate of Tesseract from 6.03 to 2.61 for Tamil (-3.42% relative change) and 7.61 to 4.74 for Sinhala (-2.87% relative change), as well as the word-level error rate from 39.68 to 20.61 for Tamil (-19.07% relative change) and 35.04 to 26.58 for Sinhala (-8.46% relative change) on the test set. Also, our newly created parallel corpus consists of 185.4k, 168.9k, and 181.04k sentences and 2.11M, 2.22M, and 2.33M Words in Tamil, Sinhala, and English respectively. This study shows that fine-tuning Tesseract models on multiple new fonts help to understand the texts and enhances the performance of the OCR. We made newly trained models and the source code for fine-tuning Tesseract, freely available.	7 Pages	None
Post-OCR Paragraph Recognition by Graph Convolutional Networks	2022-11-15	Show We propose a new approach for paragraph recognition in document images by spatial graph convolutional networks (GCN) applied on OCR text boxes. Two steps, namely line splitting and line clustering, are performed to extract paragraphs from the lines in OCR results. Each step uses a beta-skeleton graph constructed from bounding boxes, where the graph edges provide efficient support for graph convolution operations. With only pure layout input features, the GCN model size is 3~4 orders of magnitude smaller compared to R-CNN based models, while achieving comparable or better accuracies on PubLayNet and other datasets. Furthermore, the GCN models show good generalization from synthetic training data to real-world images, and good adaptivity for variable document styles.	Publi... Published in WACV 2022	None
A Benchmark and Dataset for Post-OCR text correction in Sanskrit	2022-11-15	Show Sanskrit is a classical language with about 30 million extant manuscripts fit for digitisation, available in written, printed or scannedimage forms. However, it is still considered to be a low-resource language when it comes to available digital resources. In this work, we release a post-OCR text correction dataset containing around 218,000 sentences, with 1.5 million words, from 30 different books. Texts in Sanskrit are known to be diverse in terms of their linguistic and stylistic usage since Sanskrit was the 'lingua franca' for discourse in the Indian subcontinent for about 3 millennia. Keeping this in mind, we release a multi-domain dataset, from areas as diverse as astronomy, medicine and mathematics, with some of them as old as 18 centuries. Further, we release multiple strong baselines as benchmarks for the task, based on pre-trained Seq2Seq language models. We find that our best-performing model, consisting of byte level tokenization in conjunction with phonetic encoding (Byt5+SLP1), yields a 23% point increase over the OCR output in terms of word and character error rates. Moreover, we perform extensive experiments in evaluating these models on their performance and analyse common causes of mispredictions both at the graphemic and lexical levels. Our code and dataset is publicly available at https://github.com/ayushbits/pe-ocr-sanskrit.	Findi... Findings of EMNLP, 2022. Code and Data: https://github.com/ayushbits/pe-ocr-sanskrit	Code Link
Levenshtein OCR	2022-11-14	Show A novel scene text recognizer based on Vision-Language Transformer (VLT) is presented. Inspired by Levenshtein Transformer in the area of NLP, the proposed method (named Levenshtein OCR, and LevOCR for short) explores an alternative way for automatically transcribing textual content from cropped natural images. Specifically, we cast the problem of scene text recognition as an iterative sequence refinement process. The initial prediction sequence produced by a pure vision model is encoded and fed into a cross-modal transformer to interact and fuse with the visual features, to progressively approximate the ground truth. The refinement process is accomplished via two basic character-level operations: deletion and insertion, which are learned with imitation learning and allow for parallel decoding, dynamic length change and good interpretability. The quantitative experiments clearly demonstrate that LevOCR achieves state-of-the-art performances on standard benchmarks and the qualitative analyses verify the effectiveness and advantage of the proposed LevOCR algorithm. Code is available at https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/OCR/LevOCR.	Accepted by ECCV2022	Code Link
Rerunning OCR: A Machine Learning Approach to Quality Assessment and Enhancement Prediction	2022-10-31	Show Iterating with new and improved OCR solutions enforces decision making when it comes to targeting the right candidates for reprocessing. This especially applies when the underlying data collection is of considerable size and rather diverse in terms of fonts, languages, periods of publication and consequently OCR quality. This article captures the efforts of the National Library of Luxembourg to support those targeting decisions. They are crucial in order to guarantee low computational overhead and reduced quality degradation risks, combined with a more quantifiable OCR improvement. In particular, this work explains the methodology of the library with respect to text block level quality assessment. Through extension of this technique, a regression model, that is able to take into account the enhancement potential of a new OCR engine, is also presented. They both mark promising approaches, especially for cultural institutions dealing with historical data of lower quality.	Journ... Journal of Data Mining and Digital Humanities; Minor revision	None
OCR-VQGAN: Taming Text-within-Image Generation	2022-10-26	Show Synthetic image generation has recently experienced significant improvements in domains such as natural image or art generation. However, the problem of figure and diagram generation remains unexplored. A challenging aspect of generating figures and diagrams is effectively rendering readable texts within the images. To alleviate this problem, we present OCR-VQGAN, an image encoder, and decoder that leverages OCR pre-trained features to optimize a text perceptual loss, encouraging the architecture to preserve high-fidelity text and diagram structure. To explore our approach, we introduce the Paper2Fig100k dataset, with over 100k images of figures and texts from research papers. The figures show architecture diagrams and methodologies of articles available at arXiv.org from fields like artificial intelligence and computer vision. Figures usually include text and discrete objects, e.g., boxes in a diagram, with lines and arrows that connect them. We demonstrate the effectiveness of OCR-VQGAN by conducting several experiments on the task of figure reconstruction. Additionally, we explore the qualitative and quantitative impact of weighting different perceptual metrics in the overall loss function. We release code, models, and dataset at https://github.com/joanrod/ocr-vqgan.	Paper... Paper accepted at WACV 2023	Code Link
OCR-free Document Understanding Transformer	2022-10-06	Show Understanding document images (e.g., invoices) is a core but challenging task since it requires complex functions such as reading text and a holistic understanding of the document. Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs. Although such OCR-based approaches have shown promising performance, they suffer from 1) high computational costs for using OCR; 2) inflexibility of OCR models on languages or types of document; 3) OCR error propagation to the subsequent process. To address these issues, in this paper, we introduce a novel OCR-free VDU model named Donut, which stands for Document understanding transformer. As the first step in OCR-free VDU research, we propose a simple architecture (i.e., Transformer) with a pre-training objective (i.e., cross-entropy loss). Donut is conceptually simple yet effective. Through extensive experiments and analyses, we show a simple OCR-free VDU model, Donut, achieves state-of-the-art performances on various VDU tasks in terms of both speed and accuracy. In addition, we offer a synthetic data generator that helps the model pre-training to be flexible in various languages and domains. The code, trained model and synthetic data are available at https://github.com/clovaai/donut.	ECCV ... ECCV 2022. (v5) update table 2 and figures; add LayoutLM and update scores with the latest test script at https://github.com/clovaai/donut	Code Link
Character decomposition to resolve class imbalance problem in Hangul OCR	2022-09-28	Show We present a novel approach to OCR(Optical Character Recognition) of Korean character, Hangul. As a phonogram, Hangul can represent 11,172 different characters with only 52 graphemes, by describing each character with a combination of the graphemes. As the total number of the characters could overwhelm the capacity of a neural network, the existing OCR encoding methods pre-define a smaller set of characters that are frequently used. This design choice naturally compromises the performance on long-tailed characters in the distribution. In this work, we demonstrate that grapheme encoding is not only efficient but also performant for Hangul OCR. Benchmark tests show that our approach resolves two main problems of Hangul OCR: class imbalance and target class selection.	ECCV ... ECCV 2022 TiE workshop	None
OCR for TIFF Compressed Document Images Directly in Compressed Domain Using Text segmentation and Hidden Markov Model	2022-09-13	Show In today's technological era, document images play an important and integral part in our day to day life, and specifically with the surge of Covid-19, digitally scanned documents have become key source of communication, thus avoiding any sort of infection through physical contact. Storage and transmission of scanned document images is a very memory intensive task, hence compression techniques are being used to reduce the image size before archival and transmission. To extract information or to operate on the compressed images, we have two ways of doing it. The first way is to decompress the image and operate on it and subsequently compress it again for the efficiency of storage and transmission. The other way is to use the characteristics of the underlying compression algorithm to directly process the images in their compressed form without involving decompression and re-compression. In this paper, we propose a novel idea of developing an OCR for CCITT (The International Telegraph and Telephone Consultative Committee) compressed machine printed TIFF document images directly in the compressed domain. After segmenting text regions into lines and words, HMM is applied for recognition using three coding modes of CCITT- horizontal, vertical and the pass mode. Experimental results show that OCR on pass modes give a promising results.	The p... The paper has 14 figures and 1 table	None
Figure and Figure Caption Extraction for Mixed Raster and Vector PDFs: Digitization of Astronomical Literature with OCR Features	2022-09-09	Show Scientific articles published prior to the "age of digitization" in the late 1990s contain figures which are "trapped" within their scanned pages. While progress to extract figures and their captions has been made, there is currently no robust method for this process. We present a YOLO-based method for use on scanned pages, post-Optical Character Recognition (OCR), which uses both grayscale and OCR-features. When applied to the astrophysics literature holdings of the Astrophysics Data System (ADS), we find F1 scores of 90.9% (92.2%) for figures (figure captions) with the intersection-over-union (IOU) cut-off of 0.9 which is a significant improvement over other state-of-the-art methods.	16 pa... 16 pages, 3 figures, accepted to TPDL 2022	None
An End-to-End OCR Framework for Robust Arabic-Handwriting Recognition using a Novel Transformers-based Model and an Innovative 270 Million-Words Multi-Font Corpus of Classical Arabic with Diacritics	2022-08-26	Show This research is the second phase in a series of investigations on developing an Optical Character Recognition (OCR) of Arabic historical documents and examining how different modeling procedures interact with the problem. The first research studied the effect of Transformers on our custom-built Arabic dataset. One of the downsides of the first research was the size of the training data, a mere 15000 images from our 30 million images, due to lack of resources. Also, we add an image enhancement layer, time and space optimization, and Post-Correction layer to aid the model in predicting the correct word for the correct context. Notably, we propose an end-to-end text recognition approach using Vision Transformers as an encoder, namely BEIT, and vanilla Transformer as a decoder, eliminating CNNs for feature extraction and reducing the model's complexity. The experiments show that our end-to-end model outperforms Convolutions Backbones. The model attained a CER of 4.46%.		None
DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding	2022-07-14	Show This paper presents DavarOCR, an open-source toolbox for OCR and document understanding tasks. DavarOCR currently implements 19 advanced algorithms, covering 9 different task forms. DavarOCR provides detailed usage instructions and the trained models for each algorithm. Compared with the previous opensource OCR toolbox, DavarOCR has relatively more complete support for the sub-tasks of the cutting-edge technology of document understanding. In order to promote the development and application of OCR technology in academia and industry, we pay more attention to the use of modules that different sub-domains of technology can share. DavarOCR is publicly released at https://github.com/hikopensource/Davar-Lab-OCR.	Short... Short paper, Accept by ACM MM2022	Code Link
Toward the Optimized Crowdsourcing Strategy for OCR Post-Correction	2022-06-27	Show Digitization of historical documents is a challenging task in many digital humanities projects. A popular approach for digitization is to scan the documents into images, and then convert images into text using Optical Character Recognition (OCR) algorithms. However, the outcome of OCR processing of historical documents is usually inaccurate and requires post-processing error correction. This study investigates how crowdsourcing can be utilized to correct OCR errors in historical text collections, and which crowdsourcing methodology is the most effective in different scenarios and for various research objectives. A series of experiments with different micro-task's structures and text lengths was conducted with 753 workers on the Amazon's Mechanical Turk platform. The workers had to fix OCR errors in a selected historical text. To analyze the results, new accuracy and efficiency measures have been devised. The analysis suggests that in terms of accuracy, the optimal text length is medium (paragraph-size) and the optimal structure of the experiment is two-phase with a scanned image. In terms of efficiency, the best results were obtained when using longer text in the single-stage structure with no image. The study provides practical recommendations to researchers on how to build the optimal crowdsourcing task for OCR post-correction. The developed methodology can also be utilized to create golden standard historical texts for automatic OCR post-correction. This is the first attempt to systematically investigate the influence of various factors on crowdsourcing-based OCR post-correction and propose an optimal strategy for this process.	25 pa... 25 pages, 12 figures, 1 table	None
Towards Optimizing OCR for Accessibility	2022-06-24	Show Visual cues such as structure, emphasis, and icons play an important role in efficient information foraging by sighted individuals and make for a pleasurable reading experience. Blind, low-vision and other print-disabled individuals miss out on these cues since current OCR and text-to-speech software ignore them, resulting in a tedious reading experience. We identify four semantic goals for an enjoyable listening experience, and identify syntactic visual cues that help make progress towards these goals. Empirically, we find that preserving even one or two visual cues in aural form significantly enhances the experience for listening to print content.		None
PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System	2022-06-14	Show Optical character recognition (OCR) technology has been widely used in various scenes, as shown in Figure 1. Designing a practical OCR system is still a meaningful but challenging task. In previous work, considering the efficiency and accuracy, we proposed a practical ultra lightweight OCR system (PP-OCR), and an optimized version PP-OCRv2. In order to further improve the performance of PP-OCRv2, a more robust OCR system PP-OCRv3 is proposed in this paper. PP-OCRv3 upgrades the text detection model and text recognition model in 9 aspects based on PP-OCRv2. For text detector, we introduce a PAN module with large receptive field named LK-PAN, a FPN module with residual attention mechanism named RSE-FPN, and DML distillation strategy. For text recognizer, the base model is replaced from CRNN to SVTR, and we introduce lightweight text recognition network SVTR LCNet, guided training of CTC by attention, data augmentation strategy TextConAug, better pre-trained model by self-supervised TextRotNet, UDML, and UIM to accelerate the model and improve the effect. Experiments on real data show that the hmean of PP-OCRv3 is 5% higher than PP-OCRv2 under comparable inference speed. All the above mentioned models are open-sourced and the code is available in the GitHub repository PaddleOCR which is powered by PaddlePaddle.	arXiv... arXiv admin note: text overlap with arXiv:2109.03144	None
An Evaluation of OCR on Egocentric Data	2022-06-11	Show In this paper, we evaluate state-of-the-art OCR methods on Egocentric data. We annotate text in EPIC-KITCHENS images, and demonstrate that existing OCR methods struggle with rotated text, which is frequently observed on objects being handled. We introduce a simple rotate-and-merge procedure which can be applied to pre-trained OCR models that halves the normalized edit distance error. This suggests that future OCR attempts should incorporate rotation into model design and training procedures.	Exten... Extended Abstract, EPIC workshop at CVPR 22	None
Detection Masking for Improved OCR on Noisy Documents	2022-05-17	Show Optical Character Recognition (OCR), the task of extracting textual information from scanned documents is a vital and broadly used technology for digitizing and indexing physical documents. Existing technologies perform well for clean documents, but when the document is visually degraded, or when there are non-textual elements, OCR quality can be greatly impacted, specifically due to erroneous detections. In this paper we present an improved detection network with a masking system to improve the quality of OCR performed on documents. By filtering non-textual elements from the image we can utilize document-level OCR to incorporate contextual information to improve OCR results. We perform a unified evaluation on a publicly available dataset demonstrating the usefulness and broad applicability of our method. Additionally, we present and make publicly available our synthetic dataset with a unique hard-negative component specifically tuned to improve detection results, and evaluate the benefits that can be gained from its usage		None
OCR Synthetic Benchmark Dataset for Indic Languages	2022-05-05	Show We present the largest publicly available synthetic OCR benchmark dataset for Indic languages. The collection contains a total of 90k images and their ground truth for 23 Indic languages. OCR model validation in Indic languages require a good amount of diverse data to be processed in order to create a robust and reliable model. Generating such a huge amount of data would be difficult otherwise but with synthetic data, it becomes far easier. It can be of great importance to fields like Computer Vision or Image Processing where once an initial synthetic data is developed, model creation becomes easier. Generating synthetic data comes with the flexibility to adjust its nature and environment as and when required in order to improve the performance of the model. Accuracy for labeled real-time data is sometimes quite expensive while accuracy for synthetic data can be easily achieved with a good score.		None