This project is a web application that uses a pre-trained machine learning model to detect handwritten digits from images. It is implemented using Flask, TensorFlow, and Bootstrap.
- Clone the repository:
git clone https://github.com/nv21053/MNIST-Handwritten-Digits-Detector.git
- Install the dependencies:
pip install -r requirements.txt
- Download the pre-trained model file (
mnist_model.h5
) and place it in the project root directory.
- Run the Flask web server:
python app.py
-
Open your web browser and navigate to
http://localhost:5000
. -
Choose an image of a handwritten digit and click the "Submit" button.
-
The application will predict the digit and display the result along with the probabilities for each digit.
-
To try again, click the "Try Again" button.
-
app.py
: The Flask application script. -
mnist_model.h5
: The pre-trained machine learning model for digit recognition. -
templates/index.html
: The HTML template for the web application.
- Flask: Web framework for Python.
- TensorFlow: Deep learning library for machine learning tasks.
- Pillow: Python Imaging Library for image processing.
- Flask-Bootstrap: Integration of Bootstrap with Flask.
Contributions are welcome! If you find any issues or have suggestions for improvement, please create an issue or submit a pull request.
This is a Flask.
- Python
- Flask
- Install Python requirements
pip install -r requirements.txt
- Start the server for development
python3 main.py