Handwritten Digit Recognition

Overview

This project aims to develop a machine learning model to recognize handwritten digits using the MNIST dataset. The MNIST dataset contains 60,000 training images and 10,000 testing images of handwritten digits (0-9), each image being 28x28 pixels in size.

Key Features

• Data Preprocessing: Normalizing the images and reshaping the data to include the channel dimension.
• Model Building: Training a Convolutional Neural Network (CNN) to recognize handwritten digits.
• Model Evaluation: Assessing model performance using accuracy, loss, classification report, and confusion matrix.
• Model Visualization: Visualizing training history and confusion matrix.

Installation

Clone the Repository

git clone https://github.com/your-username/handwritten-digit-recognition.git
cd handwritten-digit-recognition

Set Up a Virtual Environment

python3 -m venv venv
source venv/bin/activate  # On Windows use `venv\Scripts\activate`

Install Required Libraries

pip install -r requirements.txt

Usage

Run the Jupyter Notebook

1. Open the Jupyter notebook in your Google Colab or local environment.
2. Run the cells step-by-step to preprocess the data, train the model, evaluate its performance, and visualize the results.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License.

Acknowledgements

• The MNIST dataset is provided by Yann LeCun and Corinna Cortes.
• The developers of TensorFlow for their deep learning framework.

Contact

For any questions or feedback, please contact:

• Name: Zeeshan Ahmad
• Email: [email protected]
• GitHub: ziishanahmad
• LinkdeIn: ziishanahmad