2017/08/13 by Maciej A. Czyzewski, Czyzewski, Maciej A., Artur Laskowski +3
Computer Science · Engineering · #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image and Object Detection Techniques #Industrial Vision Systems and Defect Detection
paper · pdf · doi:10.48550/arxiv.1708.03898
openalex publication_date 2017/08/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Chessboard and chess piece recognition is a computer vision problem that has\nnot yet been efficiently solved. However, its solution is crucial for many\nexperienced players who wish to compete against AI bots, but also prefer to\nmake decisions based on the analysis of a physical chessboard. It is also\nimportant for organizers of chess tournaments who wish to digitize play for\nonline broadcasting or ordinary players who wish to share their gameplay with\nfriends. Typically, such digitization tasks are performed by humans or with the\naid of specialized chessboards and pieces. However, neither solution is easy or\nconvenient. To solve this problem, we propose a novel algorithm for digitizing\nchessboard configurations.\n We designed a method that is resistant to lighting conditions and the angle\nat which images are captured, and works correctly with numerous chessboard\nstyles. The proposed algorithm processes pictures iteratively. During each\niteration, it executes three major sub-processes: detecting straight lines,\nfinding lattice points, and positioning the chessboard. Finally, we identify\nall chess pieces and generate a description of the board utilizing standard\nnotation. For each of these steps, we designed our own algorithm that surpasses\nexisting solutions. We support our algorithms by utilizing machine learning\ntechniques whenever possible.\n The described method performs extraordinarily well and achieves an accuracy\nover 99.5 % for detecting chessboard lattice points (compared to the 74 %\nfor the best alternative), 95 % (compared to 60 % for the best alternative)\nfor positioning the chessboard in an image, and almost 95 % for chess piece\nrecognition.\n