Merge branch 'staging' of https://github.com/microsoft/computervision-recipes into staging

Author: seanytak

contrib/README.md

@@ -10,7 +10,8 @@ Each project should live in its own subdirectory ```/contrib/<project>``` and co
 |---|---|---|
 | [Crowd counting](crowd_counting) | Counting the number of people in low-crowd-density (e.g. less than 10 people) and high-crowd-density (e.g. thousands of people) scenarios. | [![Build Status](https://dev.azure.com/team-sharat/crowd-counting/_apis/build/status/lixzhang.cnt?branchName=lixzhang%2Fsubmodule-rev3)](https://dev.azure.com/team-sharat/crowd-counting/_build/latest?definitionId=49&branchName=lixzhang%2Fsubmodule-rev3)|
 | [Action Recognition with I3D](action_recognition) | Action recognition to identify video/webcam footage from what actions are performed (e.g. "running", "opening a bottle") and at what respective start/end times. Please note, that we also have a R(2+1)D implementation of action recognition that you can find under [scenarios](../sceanrios).| |
-| [Document Image Binarization](binarization) | Binarization is a technique to segment foreground from the background pixels. A simple technique for binarization is thresholding of gray-level or color document scanned images.| |
+| [Document Image Cleanup](document_cleanup) | Given an input noisy document image, the aim of document image cleanup is to improve its readability and visibility by removing the noisy elements.| |
+
 
 ## Tools
 | Directory | Project description | Build status (optional) |

contrib/binarization/README.md

@@ -0,0 +1,16 @@
+# Document Image Cleanup
+Given an input noisy document image, the aim of document image cleanup is to improve its readability and visibility by removing the noisy elements.
+
+## Example of document image cleanup
+
+### Noisy input images
+
+<img src="./light_weight_document_cleanup_ICDAR2021/sample_input_output/book_org.jpg" width="33%"> </img>
+<img src="./light_weight_document_cleanup_ICDAR2021/sample_input_output/writing_org.jpg" width="33%"> </img>
+<img src="./confidence_based_Sauvola_binarization/test_images/2.jpeg" width="33%"> </img>
+
+### cleanup images
+
+<img src="./light_weight_document_cleanup_ICDAR2021/sample_input_output/book_dnn.jpg" width="33%"> </img>
+<img src="./light_weight_document_cleanup_ICDAR2021/sample_input_output/writing_dnn.jpg" width="33%"> </img>
+<img src="./confidence_based_Sauvola_binarization/results/2_bin_new.png" width="33%"> </img>

contrib/binarization/confidence_based_Sauvola_binarization/Modified-Sauvola_Binarization.ipynb

@@ -0,0 +1,139 @@
+import cv2
+import os
+import random
+import numpy as np
+from random import randint
+import albumentations as A
+import numpy as np
+import cv2
+import sys
+import os
+from tqdm import tqdm
+from utils import GetOverlappingBlocks, getListOfFiles, ImageResize
+
+
+
+transform = A.Compose([
+        A.OneOf([
+            A.ISONoise(p=0.4),
+            A.JpegCompression(quality_lower=50, quality_upper=70, always_apply=False, p=0.8),
+        ], p=0.6),
+        A.OneOf([
+            A.MotionBlur(blur_limit=10,p=.8),
+            A.MedianBlur(blur_limit=3, p=0.75),
+            A.GaussianBlur(blur_limit=7, p=0.75),
+        ], p=0.8),                       
+        A.OneOf([
+            A.RandomBrightnessContrast(brightness_limit=0.3, contrast_limit=0.3,p=0.75),         
+            A.RandomShadow(num_shadows_lower=1, num_shadows_upper=18, shadow_dimension=6, p=0.85),
+        ], p=0.8),
+    ])
+
+
+
+def GenerateTrainingBlocks(data_folder,gt_folder,dataset_path='./dataset',M=256,N=256):
+	print(data_folder)
+	print('Generating training blocks!!!')
+	train_path =  dataset_path + '/' + data_folder + '_Trainblocks'
+
+	if not os.path.exists(train_path):
+		os.makedirs(train_path)
+
+
+	train_filenames = train_path + '/train_block_names.txt'
+	f = open(train_filenames, 'w')
+	
+	data_path = dataset_path + '/' + data_folder
+	gt_path = dataset_path + '/' + gt_folder
+	
+	print(data_path)
+	
+	filenames =  getListOfFiles(data_path)
+	cnt = 0
+	print(filenames)
+	for name in tqdm(filenames):
+		print(name)
+		gt_filename = gt_path + '/' + name
+		in_filename = data_path + '/' + name
+		print(gt_filename)
+		print(in_filename)
+		gt_image_initial = cv2.imread(gt_filename)
+		in_image_initial = cv2.imread(in_filename)
+		print(gt_image_initial.shape,in_image_initial.shape)
+		for scale in [0.7,1.0,1.4]: 
+			gt_image = ImageResize(gt_image_initial, scale)
+			in_image = ImageResize(in_image_initial, scale)	
+			h,w,c = in_image.shape
+			gt_img = GetOverlappingBlocks(gt_image,Part=8)
+			in_img = GetOverlappingBlocks(in_image,Part=8)
+			for i in range(len(gt_img)):           
+				train_img_path = train_path + '/block_' + str(cnt) + '.png'
+				gt_img_path = train_path + '/gtblock_' + str(cnt) + '.png'
+				cv2.imwrite(train_img_path,in_img[i])
+				#cv2.imwrite(train_img_path,PreProcessInput(in_img[i]))
+				cv2.imwrite(gt_img_path,gt_img[i])
+				t_name = 'block_' + str(cnt) + '.png'
+				f.write(t_name)
+				f.write('\n')
+				cnt += 1
+			Random_Block_Number_PerImage = int(len(gt_img)/5) 
+			for i in range(Random_Block_Number_PerImage):
+				
+				if(in_image.shape[0]-M>1 and in_image.shape[1]-N>1):
+					y = random.randint(1, in_image.shape[0]-M)  
+					x = random.randint(1, in_image.shape[1]-N)
+					in_part_img = in_image[y:y+M,x:x+N,:].copy() 
+					gt_part_img = gt_image[y:y+M,x:x+N,:].copy()
+					train_img_path = train_path + '/block_' + str(cnt) + '.png'
+					gt_img_path = train_path + '/gtblock_' + str(cnt) + '.png'
+					in_part_img = cv2.cvtColor(in_part_img, cv2.COLOR_BGR2RGB)
+					augmented_image = transform(image=in_part_img)['image']
+					augmented_image = cv2.cvtColor(augmented_image, cv2.COLOR_RGB2BGR)
+					
+					cv2.imwrite(train_img_path,augmented_image)
+					cv2.imwrite(gt_img_path,gt_part_img)	
+					t_name = 'block_' + str(cnt) + '.png'
+					f.write(t_name)
+					f.write('\n')
+					cnt += 1
+				else:
+					break
+					in_part_img = np.zeros((M,N,3),dtype=np.uint8)
+					gt_part_img = np.zeros((M,N,3),dtype=np.uint8)
+					in_part_img[:,:,:] = 255
+					gt_part_img[:,:,:] = 255
+					
+					if(in_image.shape[0]-M<=1 and in_image.shape[1]-N>1):
+						y = 0
+						x = random.randint(1, in_image.shape[1]-N)
+						in_part_img[:h,:,:] = in_image[:,x:x+N,:].copy() 
+						gt_part_img[:h,:,:] = gt_image[:,x:x+N,:].copy()
+					if(in_image.shape[0]-M>1 and in_image.shape[1]-N<=1):
+						x = 0
+						y = random.randint(1, in_image.shape[0]-M)  
+						in_part_img[:,:w,:] = in_image[y:y+M,:,:].copy() 
+						gt_part_img[:,:w,:] = gt_image[y:y+M,:,:].copy()	
+					
+					
+					train_img_path = train_path + '/block_' + str(cnt) + '.png'
+					gt_img_path = train_path + '/gtblock_' + str(cnt) + '.png'
+					in_part_img = cv2.cvtColor(in_part_img, cv2.COLOR_BGR2RGB)
+					augmented_image = transform(image=in_part_img)['image']
+					augmented_image = cv2.cvtColor(augmented_image, cv2.COLOR_RGB2BGR)
+					
+					cv2.imwrite(train_img_path,augmented_image)
+					cv2.imwrite(gt_img_path,gt_part_img)	
+					t_name = 'block_' + str(cnt) + '.png'
+					f.write(t_name)
+					f.write('\n')
+					cnt += 1
+		#print(cnt)
+ 
+            
+	f.close()
+
+	print('Total number of training blocks generated: ', cnt)
+	
+	return train_path, train_filenames
+
+