This project uses deep learning to train a model to recognize digits, and takes the help of OpenCV to process an image of a sudoku to separate out each cells for prediction. The extracted values are then solved using a backtracking algorithm. The solution is plotted on a sudoku template image and output to the user.

• OpenCV - open source image-processing framework
• Flask - web 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.txt

Go to the directory, and run the command:

$ python3 app.py

Follow the instructions in the website.