Chessboard recognition system using signature, principal component analysis and color information

Abstract

This paper aims to implement a computer vision technique to translate an image into a description that can be read by computer programs to make decisions. The proposed system is applied to chessboard with a set of objects (pieces), and outputs the pieces names, locations, in addition to the pieces' colors. The signature feature has been used to distinguish the pieces types but when the signature comes to grief, the PCA (Principal Components Analysis) is used, and then the object color is obtained. The proposed system was trained and tested using Matlab, based on a set of collected samples using chessboard images. The simulation results show the effectiveness of the proposed method to recognize the pieces locations, types, and colors.