https://github.com/cedric190703/sudokusense

This project is an OCR to detect and solve a sudoku grid in Python
https://github.com/cedric190703/sudokusense

ocr opencv python

Last synced: about 2 months ago
JSON representation

This project is an OCR to detect and solve a sudoku grid in Python

• Host: GitHub
• URL: https://github.com/cedric190703/sudokusense
• Owner: cedric190703
• Created: 2023-05-26T12:21:53.000Z (about 3 years ago)
• Default Branch: main
• Last Pushed: 2023-06-02T15:07:28.000Z (about 3 years ago)
• Last Synced: 2025-01-07T12:32:09.139Z (over 1 year ago)
• Topics: ocr, opencv, python
• Language: Python
• Homepage:
• Size: 571 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# SudokuSense :

## OCR to detect and solve a Sudoku grid with handwritten digits in Python.

## The application uses a graphical interface.

#### The user imports an image and then press the 'start' button :

### Step 1: Image processing:

####  We use filters to bring out the lines and the numbers and thus find and cut the Sudoku grid.

### Step 2 : Perspective transform :

#### Once the Sudoku grid is found we apply the perspective transform to have an image with the complete grid.

### Step 3 : Cut the grid and extract each digit of it

### Step 4 : Recognize digit for each image

#### Use CNN model to recognize each digit (28 x 28) pixels for each image of a digit

### Step 5 : Solve grid :

#### Solve the Sudoku grid with a backtracking algorithm.

### Step 6 : Display result :

#### Draw the final grid in an empty image of a Sudoku grid