[Code Addition Request]: AI SUDOKU SOLVER using cv2 and Tensorflow

[Tusharb331]

Have you completed your first issue?

• I have completed my first issue

Guidelines

• I have read the guidelines
• I have the link to my latest merged PR

Latest Merged PR Link

NA / Review ongoing for #722

Project Description

Feature

Implement a computer vision module that can automatically extract Sudoku puzzles from images and preprocess them for solving. This feature would enhance the usability of the solver by allowing users to input images of Sudoku puzzles directly.

Solution

I propose adding a computer vision module using OpenCV and TensorFlow. This module will:

• Detect and extract the Sudoku grid from an input image.
• Use the pre-trained TensorFlow model for digit recognition.
• Preprocess the extracted grid, identifying each cell and recognizing digits using the model.
• Output a structured Sudoku grid ready for solving with the existing AI solver.

Approach to be followed (optional)

1. Image Preprocessing: Use OpenCV to convert the image to grayscale, apply Gaussian blurring, and use edge detection to find the Sudoku grid.
2. Perspective Transformation: Correct any distortion using perspective transformation to isolate the grid.
3. Digit Recognition: Use the TensorFlow model to recognize digits in each cell.
4. Integration: Pass the recognized digits into the solver for further processing.
5. Testing: Test the module with various images to ensure robust performance across different lighting and angles.
6. Documentation: Update the README with instructions on how to use the image-based input feature.

Additional context

This feature will require libraries like OpenCV for image processing and TensorFlow for digit recognition. The existing dependencies such as numpy, Pillow, and h5py will also support this implementation. By leveraging these tools, users can solve Sudoku puzzles directly from photographs, making the solver more versatile and accessible.

Full Name

Tushar Bansal

Participant Role

Gssoc-ext, hacktobrefest

[github-actions]

🙌 Thank you for bringing this issue to our attention! We appreciate your input and will investigate it as soon as possible.

Feel free to join our community on Discord to discuss more!