11–17 of 17 posts
Hey, thanks for sharing this! I was thinking of creating a visual minesweeper solver as a web app and for sure I’m going to check your notebook ;-) ps1. As commented, I don’t have a sudoku available to try this. ps2. Yes, it’s cheating but we’re doing it for learning.
generally, when adding post scriptums, p.s. notes, it's common to add a p for each following note. So, p.s., p.p.s. etc :)
I think it would be super helpful to have an example puzzle there so one can quickly try it out without having to find a sudoku puzzle elsewhere
Yeah that's good idea, thanks for the suggestion. I even went out and bought a puzzle book while building this, so it's definitely not something most people have around.
I'm partial to "Patterns" myself, though it definitely needs a mouse or trackpad (preferably the former).
I think it would be super helpful to have an example puzzle there so one can quickly try it out without having to find a sudoku puzzle elsewhere
1) The half transparent green font color is really hard to read over a white background.
2) It fails to recongize already filled in squares and tries to change them. The source is computer generated and the image is pretty clear. It seems like a best case scenario for digit recongnition, nevertheless it fails.
3) It constantly re-evaluates while I'm trying to hold the puzzle up to the camera with varying degrees of success. Too fast for me to get a screen grab when I see a successful attempt among all the failures.
Cool project though! I was excited to try it :)
I made a similar thing a while back - works really well. https://www.atomic14.com/2020/07/25/browser-ar-sudoku.html You can see it in action here: https://sudoku.cmgresearch.com/ (assuming it still works - haven't tried it for a while).
Great post btw, very detailed.
Here are a couple attempts trying to solve an NYT hard sudoku puzzle: https://ibb.co/gtJghBP https://ibb.co/9nvHT1P 1) The half transparent green font color is really hard to read over a white background. 2) It fails to recongize already filled in squares and tries to change them. The source is computer generated and the image is pretty clear. It seems like a best case scenario for digit recongnition, nevertheless it…
I've recently made a change to try to improve results (Specifically the thresholding step when it's processing the image).
For me it's now finding the grid a bit more consistently, though your mileage may vary.
I've noticed the digit recognition still struggles a bit when looking at a screen though. Perhaps I need to get a bit more data for training the model.