Chinese chess recognition algorithm based on computer vision

This paper introduces the Chinese chess recognition algorithm based on computer vision and image processing. In order to simplify processing and enhance efficiency, the images of chessboard and chessman need preprocessing in advance. The steps of preprocessing include of transformation from color images to gray images, images filtering with mean filter or median filter, and binaryzation of the gray images. The edges of chessboard and chessman are able to be extracted from the binarized images by image segmentation. Then the location of center of chessman and the circle edge of chessman can be calculated with an advanced Hough transformation, which can ascertain the location of chessman in the chessboard and the size of each chessman. According to the features of chess images, main recognition method is to analyze the radial chess pixel statistical data with mathematical morphology. Because the values of pixel coordination in any angle of chessman can keep same and stable, the recognition algorithm should be with a good recognition rate from the experimental results. The advanced and modified recognition algorithm is proved to be practical and applicative by the experimentation of computer vision system in Chinese chess games provided in this paper.