CNN-powered Math Expression Translator

This web application (Project for Sistemas Inteligentes at UPM) uses a Convolutional Neural Network (CNN) to translate handwritten math equations into LaTeX and Python function code.

Demo

You can try out the demo here.

Table of Contents

• API Endpoints
• Contributing
• License

API Endpoints

Upload File

• URL: /upload
• Method: POST
• Description: Upload a file to the server.
• Request:
  • file: The file to upload.
• Response:

  {
      "message": "File uploaded successfully!"
  }

Process Image

• URL: /process
• Method: GET
• Description: Process the uploaded image.
• Response:

  {
      "message": "Image processed successfully!",
      "num_segments": "<number_of_segments>"
  }

Download Image

• URL: /download
• Method: GET
• Description: Download processed images.
• Parameters:
  • image: The type of image to download (processed, contours, segmented).
  • n: The segment number (for segmented images).
• Response: The requested image file.

Predict

• URL: /predict
• Method: GET
• Description: Get the LaTeX and Python function code for the predicted equation.
• Response:

  {
      "latex": "<latex_code>",
      "python": "<python_function_code>"
  }

Contributing

Contributions are welcome! Please open an issue or submit a pull request.

License

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