DigitEyes

This Java software is designed to extract digits from handwritten images. It includes a simple user interface where users can select an image containing single handwritten digit, and the software will display the extracted digit as output.

Features

1. Handwritten digit extraction using Sobel algorithm for edge detection.
2. Decision tree algorithm for digit classification.
3. User-friendly UI for easy image selection and output display.

Dataset Used for Training

The model was trained using the MNIST dataset, which consists of 60,000 handwritten digit images. You can find the MNIST dataset. (https://www.kaggle.com/datasets/oddrationale/mnist-in-csv).

Usage

• Clone the repository to your local machine.
• Open the project in your preferred Java IDE.
• Compile and run the MainWithUI.java file.
• Select an image containing handwritten digits using the UI.
• The software will process the image and display the extracted digits as output.

Requirements

1. Java Development Kit (JDK)
2. Any Java IDE (e.g., Eclipse, IntelliJ IDEA) or text editor
3. MNIST dataset (optional for training)

Contributing

Contributions are welcome! If you have any suggestions, bug fixes, or improvements, please feel free to open an issue or submit a pull request.