Re: [Computer-go] [ANN] Imago - Go board optical recognition
Hi Josef, and everybody! I am Mario Corsolini, the other author of PhotoKifu. I am aware our program was a little hidden in the Internet, mainly because until few weeks ago only an Italian version existed. Now you can download the international (EN/IT) version from my website: http://www.oipaz.net/PhotoKifu.html Within few days v2.10 will be available, featuring an improved recognition routine (as previously stated by Andrea), as well as various bugfixes. After the tests in Pisa we will be able to provide more details, re its reliability. For the moment I just want to point out that PhotoKifu still requires a human operator: pictures must be shot during the game, then transferred into a computer and analysed by our program. In order to achieve a higher level of automatism we must complete VideoKifu, which at present is in a very early stage of development. I suppose in ECG2015 we will have a working prototype for a demonstration, at best: an official release will most likely be ready before ECG2016. Best regards, Dr Mario Corsolini ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
Re: [Computer-go] [ANN] Imago - Go board optical recognition
Hello Andrea, I happen to be organizing the technical section of EGC2015, and we would certainly be really glad to use automatic transcription and internet broadcasting, as this would make it possible to broadcast more boards with less manpower (hopefully more precisely, it is common that one human transcribes two boards and there are mistakes e.g. in ko fights). We were actually considering this option ourselves, but I concluded that there does not exist a production-ready solution yet. I have missed photokifu as well in my research (and to be honest, it is hard to find your app even if I know its name, mostly because there seems to be an iApp called the same). However, were we to use automatic transcription, we would need to make sure it works reliably. Best regards, Josef Dne so 17. 1. 2015 21:38 uživatel Andrea Carta andrea.ca...@mclink.it napsal: Marc Landgraf mahrgell87 at gmail.com writes: Out of curiosity...In the picture you linked ( http://i59.tinypic.com/10cnu5c.jpg ), how does your program read the position in the top left, considering the illegal stone there? Or does it not have any Go rules knowledge and leaves the interpretation to the user? In that case it may create .sgf with illegal moves in it. Considering during a regular game, you will actually snapshot illegal positions a few times (when you take a picture between placing the stone and removing the captures) I'm really wondering how your program handles it. Of course it is advisable to take every picture after the removal of the stones possibly captured; the program expects such stones to be removed from the goban. Otherwise, two cases are possible. First one, the player forgot to remove the stone (or did not make in time): in such a case the program detects the error and asks the user what to do next. Second, a suicide move was played (willingly or not). In such a case the program checks the rules and, if suicide is not allowed, again asks the user what to do next (otherwise it gets on). But as this particular problem does not concern the main algorithm, we have not made a final decision. There are other options on the table (for example automatic error correction/stone addition). mr. Andrea Carta ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
Re: [Computer-go] [ANN] Imago - Go board optical recognition
Here's a demonstration of some work I did for University. https://www.youtube.com/watch?v=dX6s-3Xm7xU It's done with OpenCV and I'll be happy to share the code with whoever is interested. 2015-01-18 13:18 GMT+00:00 Mario Corsolini oi...@oipaz.net: Hi Josef, and everybody! I am Mario Corsolini, the other author of PhotoKifu. I am aware our program was a little hidden in the Internet, mainly because until few weeks ago only an Italian version existed. Now you can download the international (EN/IT) version from my website: http://www.oipaz.net/PhotoKifu.html Within few days v2.10 will be available, featuring an improved recognition routine (as previously stated by Andrea), as well as various bugfixes. After the tests in Pisa we will be able to provide more details, re its reliability. For the moment I just want to point out that PhotoKifu still requires a human operator: pictures must be shot during the game, then transferred into a computer and analysed by our program. In order to achieve a higher level of automatism we must complete VideoKifu, which at present is in a very early stage of development. I suppose in ECG2015 we will have a working prototype for a demonstration, at best: an official release will most likely be ready before ECG2016. Best regards, Dr Mario Corsolini ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go -- Alexandre Nuno Milheiro de Oliveira ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
