Chessboard and Chess Piece Recognition With the Support of Neural Networks

• Autorzy: Czyżewski Maciej A. , Laskowski Artur , Wasik Szymon

Identyfikatory

DOI

10.2478/fcds-2020-0014

• Języki publikacji: EN

Abstrakty

EN

Chessboard and chess piece recognition is a computer vision problem that has not yet been efficiently solved. Digitization of a chess game state from a picture of a chessboard is a task typically performed by humans or with the aid of specialized chessboards and pieces. However, those solutions are neither easy nor convenient. To solve this problem, we propose a novel algorithm for digitizing chessboard configurations. We designed a method of chessboard recognition and pieces detection that is resistant to lighting conditions and the angle at which images are captured, and works correctly with numerous chessboard styles. Detecting the board and recognizing chess pieces are crucial steps of board state digitization. The algorithm achieves 95% accuracy (compared to 60% for the best alternative) for positioning the chessboard in an image, and almost 95% for chess pieces recognition. Furthermore, the subprocess of detecting straight lines and finding lattice points performs extraordinarily well, achieving over 99.5% accuracy (compared to the 74% for the best alternative).

Słowa kluczowe

EN

chessboard detection; chess pieces recognition; pattern recognition; chessboard recognition; chess; neural networks

• Wydawca: Wydawnictwo Politechniki Poznańskiej
• Czasopismo: Foundations of Computing and Decision Sciences
• Rocznik: 2020
• Tom: Vol. 45, No. 4
• Strony: 257--280
• Opis fizyczny: Bibliogr. 47 poz., rys., tab.

Twórcy

autor

Czyżewski Maciej A.

• Institute of Computing Science, Poznan University of Technology, Piotrowo 2, Poznan, Poland

autor

Laskowski Artur

• Institute of Computing Science, Poznan University of Technology, Piotrowo 2, Poznan, Poland
• European Center for Bioinformatics and Genomics, Poznan University of Technology, Piotrowo 2, Poznan, Poland

autor

Wasik Szymon

• European Center for Bioinformatics and Genomics, Poznan University of Technology, Piotrowo 2, Poznan, Poland

Bibliografia

• [1] Acher M. and Esnault F. Large-scale analysis of chess games with chess engines: Apreliminary report, 2016.
• [2] Arca S., Casiraghi E., and Lombardi G. Corner localization in chessboards for camera calibration. In Proceedings of International Conference on Multimedia, Image Processing and Computer Vision (IADAT-micv2005), 2005.
• [3] Bency A.J., Kwon H., Lee H., Karthikeyan S., and Manjunath B. Weakly supervised localization using deep feature maps. In European Conference on Computer Vision, pages 714-731, Springer, 2016.
• [4] Bennett S. and Lasenby J. Chess-quick and robust detection of chess-board features. Computer Vision and Image Understanding, 118:197–210, 2014.
• [5] Braje W.L., Kersten D., Tarr M.J., and Troje N.F. Illumination effects in face recognition. Psychobiology, 26(4):371-380, 1998.
• [6] Choudhury Z.H. Biometrics security based on face recognition. Master’s thesis, India, 2013.
• [7] CoolThings. Square off is a robot chess board that can move pieces on its own, November 2016.
• [8] Cour T., Lauranson R., and Vachette M. Autonomous chess-playing robot.Ecole Polytechnique, July, 2002.
• [9] Czyzewski M.A., Laskowski A., and Wasik S. Latchess 21: dataset of damaged chessboard lattice points (chessboard features) used to train laps detector (grayscale/21x21px), 2018.
• [10] Danner C. and Kafafy M. Visual chess recognition, 2015.
• [11] De la Escalera A. and Armingol J.M. Automatic chessboard detection for intrinsic andextrinsic camera parameter calibration.Sensors, 10(3):2027–2044, 2010.
• [12] Ding J. Chessvision: Chess board and piece recognition. Technical report, Stanford University, 2016.
• [13] Duda R.O. and Hart P.E. Use of the hough transformation to detect lines and curves inpictures. Commun. ACM, 15(1):11-15, Jan. 1972.
• [14] Edwards S.J. Portable game notation specification and implementation guide. Retrieved April, 4:2011, 1994.
• [15] Fernandes L.A. and Oliveira M.M. Real-time line detection through an improvedhough transform voting scheme. Pattern recognition, 41(1):299-314, 2008.
• [16] Galler B.A. and Fisher M.J. An improved equivalence algorithm. Commun. ACM, 7(5):301–303, May 1964.
• [17] Gao F., Huang T., Wang J., Sun J., Hussain A., and Yang E. Dual-branch deep convolution neural network for polarimetric SAR image classification. Applied Sciences,7(5):447, 2017.
• [18] Hamid N. and Khan N. Lsm: perceptually accurate line segment merging. Journal of Electronic Imaging, 25(6):061620, 2016.
• [19] Harris C. and Stephens M.A combined corner and edge detector. In Alvey vision conference, volume 15, pages 10-5244. Citeseer, 1988.
• [20] Jassim F.A. and Altaani F.H. Hybridization of otsu method and median filter for colorimage segmentation, 2013.
• [21] Kanchibail R., Suryaprakash S., and Jagadish S. Chess board recognition. Not publishedin journal, 2016.
• [22] Koray C. and Sumer E.A computer vision system for chess game tracking. In 21st Computer Vision Winter Workshop, Rimske Toplice, Slovenia, 2016.
• [23] Larson C. China’s massive investment in artificial intelligence has an insidious downside. Science, feb 2018.
• [24] Leonard J., Durrant-Whyte H., and Cox I. Dynamic map building for autonomous mobile robot. In IEEE International Workshop on Intelligent Robots and Systems, Towardsa New Frontier of Applications. IEEE, jul 1990.
• [25] Li Q., Zheng N., and Cheng H. Springrobot: A prototype autonomous vehicle and its algorithms for lane detection. IEEE Transactions on Intelligent Transportation Systems, 5(4):300–308, dec 2004.
• [26] Lu X., Yao J., Li K., and Li L. Cannylines: A parameter-free line segment detector.In Image Processing (ICIP), 2015 IEEE International Conference on, pages 507–511. IEEE, 2015.
• [27] Marciniak T., Chmielewska A., Weychan R., Parzych M., and Dabrowski A. Influence of low resolution of images on reliability of face detection and recognition. Multimedia Tools and Applications, 74(12):4329–4349, jul 2013.
• [28] Matuszek C., Mayton B., Aimi R., Deisenroth M.P., Bo L., Chu R., Kung M., LeGrand L., Smith J.R., and Fox D. Gambit: An autonomous chess-playing robotic system. 2011 IEEE International Conference on Robotics and Automation, pages 4291–4297, 2011.
• [29] Mietchen D., Wodak S., Wasik S., Szostak N., and Dessimoz C. Submit a topic page toplos computational biology and wikipedia. PLOS Computational Biology, 14(5):1–4, 05 2018.
• [30] Pomerleau D. and Jochem T. Rapidly adapting machine vision for automated vehicle steering. IEEE Expert, 11(2):19–27, apr 1996.
• [31] Prejzendanc T., Wasik S., and Blazewicz J. Computer representations of bioinformaticsmodels. Current Bioinformatics, 11(5):551–560, 2016.
• [32] Reza A.M. Realization of the contrast limited adaptive histogram equalization (clahe) for real-time image enhancement. Journal of VLSI signal processing systems for signal, image and video technology, 38(1):35–44, 2004.
• [33] Sen D. and Pal S.K. Gradient histogram: Thresholding in a region of interest for edgedetection. Image and Vision Computing, 28(4):677–695, 2010.
• [34] Shortis M. Calibration techniques for accurate measurements by underwater camera systems. Sensors, 15(12):30810–30826, 2015.
• [35] Soh L. Robust recognition of calibration charts. In 6th International Conference on Image Processing and its Applications. IEE, 1997.
• [36] Stark J.A. Adaptive image contrast enhancement using generalizations of histogram equalization. IEEE Transactions on Image Processing, 9(5):889–896, May 2000.
• [37] Szostak N., Wasik S., and Blazewicz J. Hypercycle. PLOS Computational Biology, 12(4):e1004853, apr 2016.
• [38] Tam K.Y., Lay J.A., and Levy D. Automatic grid segmentation of populated chess-board taken at a lower angle view. In Computing: Techniques and Applications, 2008.DICTA’08. Digital Image, pages 294-299. IEEE, 2008.
• [39] Tarjan R.E. Efficiency of a good but not linear set union algorithm. J. ACM, 22(2):215-225, Apr. 1975.
• [40] Tavares J.M.R.S. and Padilha A.J.M.N. A new approach for merging edge linesegments. Proceedings RecPad’95, Aveiro, 1995.
• [41] Urting D. and Berbers Y. Marineblue: A low-cost chess robot. In Robotics and Applications, 2003.
• [42] Wasik S., Fratczak F., Krzyskow J., and Wulnikowski J. Inferring Mathematical Equations Using Crowdsourcing. PLOS ONE, 10(12):e0145557, dec 2015.
• [43] Wasik S., Prejzendanc T., and Blazewicz J. ModeLang - a new approach for experts-friendly viral infections modeling. Computational and Mathematical Methods in Medicine, 2013:8, 2013.
• [44] Wiens D.P. Asymptotics of generalized m-estimation of regression and scale with fixedcarriers, in an approximately linear model. Statistics & probability letters, 30(3):271–285, 1996.
• [45] Wu Q., Zhang J., Lai Y.-K., Zheng J., and Cai J. Alive caricature from 2d to 3d, 2018.
• [46] Zhang Z. A flexible new technique for camera calibration. IEEE Transactions on patternan alysis and machine intelligence, 22(11):1330–1334, 2000.
• [47] Zhao F., Wei C., Wang J., and Tang J. An automated x-corner detection algorithm (axda). JSW, 6(5):791–797, 2011.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).