README.md

metadata

title: EMNIST Predictor
emoji: 🖊️
colorFrom: blue
colorTo: gray
sdk: docker
app_port: 7860

Optical Character Recognition

Use the tool live here.

This is an optical character recognition (OCR) tool that extracts characters from drawings. It's made with FastAPI for the backend, vanilla JS/HTML for the frontend, and the model was trained using PyTorch.

The project creates a canvas to draw on, converts the drawing to a usable 28x28 pixel format, and sends it to the backend for prediction.

The only two routes for the backend are / for the home page and /predict for prediction API. The prediction route recognizes all English characters and digits. For more details on the architecture, the dataset, and training process, check out this writeup, which presents the simpler of two models trained for my writeup on CNNs.

Usage

Once again, the tool is hosted on this webpage for easy access.

Draw the character you want to recognize on the left canvas. The right canvas will display the top-k predictions, where k can be adjusted using the slider below it. The slider is capped at 15 since, after 15, all of the predictions are basically guaranteed to be at 0% probability.

To run this project locally, take the following steps:

Installation

1. Clone this repository.

   git clone https://github.com/intelligent-username/OCR
   cd OCR
   

2. Install the Python dependencies to a virtual environment.

   python -m venv OCR-env
   OCR-env\Scripts\activate        # On Windows
   source OCR-env/bin/activate     # On mac/Linux
   pip install -r requirements.txt
   

3. Run the backend.

   uvicorn backend.app:app --reload
   

4. Once the backend is running, go to http://127.0.0.1:8000/ in your web browser to access the frontend. This link will appear in the terminal when you run the backend.

License

This project is licensed under the MIT License. For details, see the LICENSE file.