Python, OpenCV and Sudokus

Question

With the PDF below, I would like to do the following things.

Localize the four sudoku grids so as to treat each of them separately.
For each grid picture, I would like to obtain a matrix of the pictures corresponding to each cell.
Finally, I would like to "find" the values printed in each cell.

The problem is that I'm a real beginner with OpenCV (I've bought a book about OpenCV with Python but I've not received it yet).

I'm not a beginner in Python, neither in math so every clue is welcomed.

enter image description here

score 1 · Accepted Answer · answered Feb 17 '13 at 21:48

1

You're in luck:

Python 3.x isn't supported by OpenCV though.

answered Feb 17 '13 at 21:48

b_m

Thanks for the link. I've already done my solver. There is still one question. How to localize each grid independently ? – Feb 17 '13 at 21:54
I believe that part 2 covers that too. He does this for one grid, but you should have no problem doing that for all four. – b_m Feb 17 '13 at 22:00
I will play with all of this as soon as possible. – Feb 17 '13 at 22:05
Just to keep this answer up to date, now OpenCV supports Python 3 with OpenCV 3 Beta. – Julien Palard Oct 22 '14 at 22:04

score 0 · Answer 2 · answered Feb 17 '13 at 22:00

0

tesseract has nice python bindings, too (and is more specialized on that 'ocr' job ;)

welcome to opencv, though !

answered Feb 17 '13 at 22:00

berak

well, it can do letters, it can do digits, too – berak Feb 17 '13 at 22:23
Even if it is not summer time, it is christmas time ! – Feb 17 '13 at 23:42
@projetmbc : manually prepare digit OCR in opencv : http://stackoverflow.com/questions/9413216/simple-digit-recognition-ocr-in-opencv-python/9620295#9620295 – Abid Rahman K Feb 18 '13 at 01:57
I will play with that too. – Feb 18 '13 at 09:40

2 Answers2