Algorithm of Military Chess Pieces Discrimination Based on Image Processing

Abstract

In order to popularize the dark military chess, this paper presented a method using image processing to identify military chess pieces and determine their grade size. First, the method of scanning row and column was used to extract the image of chess pieces from original image. Two chess pieces images were separated with the method of row and column scanning, too. Next, the size of R component in two chess pieces images were calculated to determine the color of two chessmen images and the information which one is black or red was obtained. Then, two chess pieces images were processed with gray and binarization respectively, and the size of two chess pieces images were normalized. At the last, two chess pieces pictures were matched with the templates in corresponding templates library that created in advance. The chinese character of chess pieces can be identified. After two chess pieces images were recognized, and the grade size of two chess pieces were determined according to the rules of military chess. Experimental results show that the proposed method has a high recognition rate which is 100% and fast processing speed which is up to 0.730594s.