Handwritten-digit-recognition

Description

This project focuses on classifying handwritten digits from the MNIST dataset. It explores and compares the performance of various machine learning algorithms, including Neural Networks, Support Vector Machines (SVM), and K-Nearest Neighbors (KNN), to determine the most effective method for recognizing digits in images.

Download the checkpoint for each model from this Google Drive link and place it in the project folder.

Features

• Data Preprocessing: Normalize image data to ensure compatibility with machine learning algorithms.

• Model Training and Evaluation: Train and evaluate various models, including Neural Networks, SVM, and KNN, for handwritten digit recognition.

• User Interface: Integrate a user-friendly interface for easy interaction and testing.

Installation

Clone the repository:

git clone https://github.com/fisherman611/handwritten-digit-recognition.git

(Optional) Install the required dependencies:

pip install -r requirements.txt

Navigate to the project directory:

cd handwritten-digit-recognition

Run the GUI on CMD (ensure that your gradio version is 3.0.0, below is an example with python 3.11):

py -3.11 GUI.py

Contributing

Contributions are welcome! If you find any issues or have suggestions for improvements, please open an issue or submit a pull request.

License

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