Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Chessvision.ai – Analyze chess position from websites, images or video

chessvision.ai

Post reply on HN
Print view View original

21–30 of 51 posts

Re: Chessvision.ai – Analyze chess position from websites, images or video

#21

Post by smallgovt »

rtkwe wrote: post #19
smallgovt wrote: post #18

It’d be great to convert this into a mobile app that lets you take a photo and then loads it into a game analysis board. We would use this all the time at my local chess club. Sometimes we just want to know what the best move is and other times we want to save the game so we can continue it later. I would pay $10 or $1.99 a month for this. Food for thought!

This would be much much harder with a real board with 3D pieces.

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.

Re: Chessvision.ai – Analyze chess position from websites, images or video

#22

Post by bluGill »

pkacprzak wrote: post #9
novalis78 wrote: post #6

Earlier quoted context omitted.

That would rock for chess tournaments. Webcam next to the board and run analysis for the audience...

actually, most high-level tournaments use electronic dgt boards to solve this problem in a more flawless way

Those boards are ~$1000 each. High level tournaments use them, but low level tournaments don't unless some rich person has bought the club a bunch. Most tournaments are low level and are designed not to turn a profit: the entry fees either pay for the room rent, or go to the prize winnings: the more people who enter the more prize money there is.

Re: Chessvision.ai – Analyze chess position from websites, images or video

#23

Post by joemi »

owldimoon wrote: post #13
novalis78 wrote: post #6

Earlier quoted context omitted.

That would rock for chess tournaments. Webcam next to the board and run analysis for the audience...

Hey! I'm working on exactly this same problem for an undergraduate Computer Vision course right now. It's not going well! Chess piece recognition is hard. I definitely think the electronics approach described in the other comment is a much more reliable way to go.

If you ever do get it working, I think it'll be fun to push it to over-recognize chess games everywhere, like the deepdream stuff over-recognizing animals (or whatever) everywhere.

Re: Chessvision.ai – Analyze chess position from websites, images or video

#26

Post by rtkwe »

smallgovt wrote: post #21
rtkwe wrote: post #19

Earlier quoted context omitted.

This would be much much harder with a real board with 3D pieces.

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.

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.

Re: Chessvision.ai – Analyze chess position from websites, images or video

#27

Post by epiceric »

Maybe it's just me, but I'd be wary of any browser extension that captures and analyzes my screen over-the-wire, especially if it is closed-source like this one.

Not to say that this is necessarily malicious. But I personally wouldn't recommend this to anybody as of right now, unless you want to risk leaking potentially sensitive data to a third-party.

Re: Chessvision.ai – Analyze chess position from websites, images or video

#29

Post by tgarv »

rtkwe wrote: post #26
smallgovt wrote: post #21

Earlier quoted context omitted.

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.

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.

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.
Post reply on HN