[论文解读] Chessboard and chess piece recognition with the support of neural networks

Maciej A. Czyzewski, Artur Laskowski+1 more|arXiv (Cornell University)|Aug 13, 2017

Image and Object Detection Techniques被引用 4

一句话总结

本文提出了一种基于神经网络的鲁棒端到端方法，用于在真实世界图像中检测国际象棋棋盘并识别棋子，即使在光照和角度条件复杂的情况下也能有效工作。该方法结合了迭代线检测、格点定位以及使用自定义卷积神经网络的棋子分类，格点检测准确率超过99.5%，棋子识别准确率接近95%，显著优于现有方法。

ABSTRACT

Chessboard and chess piece recognition is a computer vision problem that has not yet been efficiently solved. However, its solution is crucial for many experienced players who wish to compete against AI bots, but also prefer to make decisions based on the analysis of a physical chessboard. It is also important for organizers of chess tournaments who wish to digitize play for online broadcasting or ordinary players who wish to share their gameplay with friends. Typically, such digitization tasks are performed by humans or with the aid of specialized chessboards and pieces. However, neither solution is easy or convenient. To solve this problem, we propose a novel algorithm for digitizing chessboard configurations. We designed a method that is resistant to lighting conditions and the angle at which images are captured, and works correctly with numerous chessboard styles. The proposed algorithm processes pictures iteratively. During each iteration, it executes three major sub-processes: detecting straight lines, finding lattice points, and positioning the chessboard. Finally, we identify all chess pieces and generate a description of the board utilizing standard notation. For each of these steps, we designed our own algorithm that surpasses existing solutions. We support our algorithms by utilizing machine learning techniques whenever possible. The described method performs extraordinarily well and achieves an accuracy over $99.5\\%$ for detecting chessboard lattice points (compared to the $74\\%$ for the best alternative), $95\\%$ (compared to $60\\%$ for the best alternative) for positioning the chessboard in an image, and almost $95\\%$ for chess piece recognition.

研究动机与目标

• 开发一种鲁棒且适用于真实世界场景的物理国际象棋棋盘数字化方法，无需专用硬件或受控成像条件。
• 解决现有国际象棋棋盘检测系统在光照变化、拍摄角度或棋盘样式差异下性能下降的局限性。
• 在棋盘定位与棋子识别两方面均超越当前最先进方法的准确率。
• 创建一个公开可获取的增强数据集，以支持未来在国际象棋棋盘识别领域的研究。
• 实现实际应用场景，如实时比赛数字化、AI对手集成以及玩家间棋局共享。

提出的方法

• 该方法通过三个核心阶段迭代处理图像：使用改进的SLID算法进行直线检测，将短段合并为更长的直线。
• 利用自定义训练的卷积神经网络（CNN）检测格点，即使在棋盘形变或部分遮挡的情况下也能识别角落。
• 通过分析检测到的直线与格点之间的几何关系实现棋盘定位，从而在各种角度和光照条件下保持鲁棒性。
• 棋子识别采用基于CNN的分类器，并通过Stockfish国际象棋引擎进行概率过滤，以排除不合理的棋局配置。
• 系统整合Stockfish的反馈以优化预测结果，显著减少常见错误，如将主教误判为兵。
• 从真实比赛转播中收集并整理了一个新颖且大规模的数据集，已公开共享以支持未来研究。

实验结果

研究问题

• RQ1 计算机视觉系统是否能在光照、角度和棋盘样式多变的真实图像中实现高精度的国际象棋棋盘检测？
• RQ2 与Hough变换或ChESS等传统方法相比，基于神经网络的格点检测器在处理形变或遮挡的角落时表现如何？
• RQ3 集成国际象棋引擎的评估能力在模糊情况下能否显著提升棋子识别的准确率？
• RQ4 在真实条件下，该方法是否能在棋盘定位与棋子分类两方面均超越现有开源解决方案？
• RQ5 该方法在实际应用中的有效性如何，例如在实时国际象棋比赛数字化或支持从物理棋盘进行人机对弈方面？

主要发现

• 所提方法在格点检测中达到99.5%的准确率，显著优于最佳替代方法（仅74%）。
• 棋盘定位准确率达到95%，而最佳现有替代方法仅为60%，表明其在拍摄角度和光照变化下具有显著鲁棒性。
• 棋子识别准确率接近95%，标志着首个可在真实世界环境中可靠部署以实现棋局数字化的方法。
• 与ChESS分类器相比，使用CNN进行格点检测使形变点的误判率降低50%以上，后者仅能识别43%的真实正例。
• 与Stockfish国际象棋引擎集成显著提升了分类性能，通过过滤低概率棋局配置，减少了常见误判错误。
• 该方法已引起实际应用关注，多名用户表示有意在真实场景中部署，且训练数据已公开以支持未来研究。