In this project, a model for digit recognition is trained using Deep Learning, and an image of a sudoku puzzle is processed using OpenCV to separate out each cell for prediction. A backtracking approach is then used to solve the extracted values. The user receives the solution mapped on an image of a sudoku template.
- Flask - web framework
- OpenCV - open source image-processing framework
- Deep Learning - Tensorflow and Keras
Go the project directory and run the command to install all the required packages. This might take some time.
pip3 install -r requirements.txtGo to the directory, and run the command:
$ python3 app.pyFollow the instructions in the website.