[Project Addition] :Real Time Sudoku Solver Using OpenCV

[abckhush]

Deep Learning Simplified Repository (Proposing new issue)

:red_circle: Project Title : Real Time Sudoku Solver Using OpenCV
:red_circle: Aim : To solve sudoku in seconds.
:red_circle: Dataset : Any Sudoku Image.
:red_circle: Approach : CNN and backtracking algorithm.

---

📍 Follow the Guidelines to Contribute in the Project :

• You need to create a separate folder named as the Project Title.
• Inside that folder, there will be four main components.
  • Images - To store the required images.
  • Dataset - To store the dataset or, information/source about the dataset.
  • Model - To store the machine learning model you've created using the dataset.
  • requirements.txt - This file will contain the required packages/libraries to run the project in other machines.
• Inside the Model folder, the README.md file must be filled up properly, with proper visualizations and conclusions.

---

:red_circle::yellow_circle: Points to Note :

• The issues will be assigned on a first come first serve basis, 1 Issue == 1 PR.
• "Issue Title" and "PR Title should be the same. Include issue number along with it.
• Follow Contributing Guidelines & Code of Conduct before start Contributing.

---

:white_check_mark: To be Mentioned while taking the issue :

• Full name : Khushi Kalra
• GitHub Profile Link : abckhush
• Email ID : kalra.khushi@outlook.comm
• Participant ID (if applicable):
• Approach for this Project : CNN and Backtracking Algorithm
• What is your participant role? (Mention the Open Source program): GSSoC 2024 Contributor

---

Happy Contributing 🚀

All the best. Enjoy your open source journey ahead. 😎

[github-actions[bot]]

Thank you for creating this issue! We'll look into it as soon as possible. Your contributions are highly appreciated! 😊

[abhisheks008]

This repo demands to implement at least 2-3 models for each and every problem statement. What are the models you are planning for this?

[abckhush]

I could do one with backtracking algorithm (brute force), then optimize it in the next, and then develop using recursion when needed in the third. These could work on a dataset of 50 difficult sudoku that I have downloaded. The only thing here would be that I wouldn't use OpenCV. Would this be ok?

[abhisheks008]

As you are going to build this solver application, a web app should be there to showcase the working of the model you are going to implement. Are you up for this?

[abckhush]

A ReactJS website with minimal UI would work.

1. If I am going to implement a web app, would I need to make different models?
2. Web App using OpenCV or manual entries of the sudoku?

[abhisheks008]

A ReactJS website with minimal UI would work.

1. If I am going to implement a web app, would I need to make different models?
2. Web App using OpenCV or manual entries of the sudoku?

Use the best model as the backend of the web app. This should be like this, user uploads an unsolved sudoku image and the model will solve the sudoku and show the user the correct result.

[abckhush]

How about I make a python application and, using the camera, user shows the image of the sudoku and using opencv it overlays the answers ?

[abhisheks008]

How about I make a python application and, using the camera, user shows the image of the sudoku and using opencv it overlays the answers ?

Cool that will work too. Showing the implementation of the model is the priority for me from a layman's perspective.

[abckhush]

Ok. Can you assign me this issue then?

[abhisheks008]

Assigned @abckhush

[github-actions[bot]]

Hello @abckhush! Your issue #774 has been closed. Thank you for your contribution!