The Journal of The Institute of Image Information and Television Engineers
Online ISSN : 1881-6908
Print ISSN : 1342-6907
ISSN-L : 1342-6907
Use of Artificial Neural Network for Unbeatable Game of Rock-Scissors-Paper
Daisuke IsayamaRyo TaguchiTaizo UmezakiMasahiro Hoguro
Author information

2011 Volume 65 Issue 2 Pages 211-217


We describe an unbeatable rock-scissors-paper (janken) game system which defeats the opponent without fail and never has any delay in the presentation of the hand. This system recognizes the shape of the opponent's hand with pictures taken by a 60-fps camera and displays the hand form that can win a game on the screen before the opponent completes their hand form. When a 60-fps camera used, the whole process, which includes image acquisition, preprocessing the image, recognition of the hand shape and a display of the winning hand form, is done within about 16 msec. The optimal display time is decided on the basis of experience, recognition of the hand form and the time needed to present one of the three symbols without giving the opponent, who has average reactions a feeling of delay.

Related papers from these authors
© 2011 The Institute of Image Information and Television Engineers
Previous article Next article