Handwritten Digit Recognition

This repository contains a Python-based project for recognizing handwritten digits using a neural network trained on the MNIST dataset. The project includes a graphical user interface (GUI) that allows users to draw or upload digits for prediction.

Features

• Interactive GUI for digit input.

• Neural network model for digit recognition.

• Pre-trained weights for quick predictions.

• Modular design for easy customization and scalability.

Files Overview

• GUI.py: Implements the graphical interface for user interaction.

• Model.py: Contains the neural network architecture.

• Prediction.py: Loads trained weights and makes predictions.

• RandInitialise.py: Initializes weights for the neural network.

• Theta1.txt & Theta2.txt: Store the pre-trained weights.

• main.py: Entry point for running the application.

• mnist-original.mat/: Includes the MNIST dataset for training and testing.

Deployment

Clone the repository:

git clone https://github.com/SankethSingh/Handwritten-digit-recognition.git

Install dependencies:

pip install numpy scipy matplotlib

Run the application:

python main.py

Contributing

Contributions are always welcome! Feel free to open issues or submit pull requests to enhance this project.

See contributing.md for ways to get started.

Please adhere to this project's code of conduct.

License

This project is licensed under the MIT License. See the LICENSE file for details.

MIT

Acknowledgements

• MNIST Dataset
• Python libraries: NumPy, SciPy, Matplotlib