Hacker News new | ask | show | jobs
by smallgovt 2635 days ago
I see. Well, one thing that may help is that 95% of chessboards (at least at the clubs I've visited) use the same piece set: https://www.amazon.com/WE-Games-Complete-Tournament-Chess/dp...

Also, a 10% error rate wouldn't be a big deal as long as it was easy to correct the position within a few seconds.

1 comments

That makes it vaguely possible yeah but going from a flat on 2D grid to a 3D set of pieces at an angle is a whole different set of problems.
Although it is more difficult in 3D, it is still a very solvable problem, that won't work always, but in 99% of cases if the camera angle is not very low.

Indeed, the checkerboard itself gives valuable information about the pose of the checkerboard, it is even used for calibration in multi-view geometry: https://en.wikipedia.org/wiki/Chessboard_detection

I wonder how much easier it would be if you narrow down the likely set of pieces for each square. There are obviously some positions for some pieces that are invalid (bishop on the wrong colored square), but there are probably a lot of other positions that are so uncommon that they could be discounted.
What would make it easier IMHO is to make it a top-down version only. Take a photo from the top, then the program breaks down the board into 8x8 squares, feeds each square into a classification algorithm that you will train on a bunch of hand labeled images. Fine tune the model as you gather more data.
The pieces look more similar from the top, though. With bad enough contrast everything is just a circle. So you need some kind of angle.
> With bad enough contrast everything is just a circle.

Yes but does real world photos ever have that poor contrast? IMO, top down photo is worth exploring.

Probably not much. How many are actually impossible if you factor in pawn promotion though? The only one that comes to mind immediately for any individual piece is pawns on their own first row and a board without two kings.
Standard object detection can't work here?
Have to detect and accurately place them in space to map them to the board.
They're on a grid though, why would this be hard?

Compared to all the other feats of machine learning that have blown my mind, parsing a photo of a limited set of a handful of different piece variants, in two colors, that located on a grid, doesn't seem too difficult.