基于卷积神经网络的棋子定位和识别方法
|
摘要
中国象棋棋子定位采用的传统图像处理方法,复杂度高;识别棋子采用的传统文字识别方法,泛化性较差、精确度较低。提出一种基于棋子颜色特征的分割方法和改进的二值图像滤波算法,实现了棋子的快速定位,不需要二次修正位置;提出一种基于卷积神经网络的棋子识别方法,该方法可以应用于不同字体的棋子识别,在更换棋子的情况下,依然可以快速、准确地识别棋子。实验结果表明,该方法的定位误差为0.51 mm,平均定位时间0.212s,对4类字体的平均棋子识别准确率为98.59%左右,证实了该方法的有效性和实用性。
The traditional image processing algorithms used for the location of Chinese chess pieces have high complexity and the traditional character recognition methods used for the recognition of chess pieces have low generalization and accuracy.A segmentation method based on chess piece color features and an improved binary image filtering algorithm are proposed to achieve the fast location of chess pieces,and the second correction of positions is not needed.A recognition method of chess pieces based on a convolutional neural network is proposed,which can be used for the recognition of chess pieces with different fonts.In the case of chess piece replacement,this method can still recognize chess pieces quickly and accurately.The experimental results show that as for the proposed method,the location error is 0.51 mm,the average location time is 0.212 s,and the average recognition accuracy of chess pieces with four types of fonts is about 98.59%.The effectiveness and practicability of this method are confirmed.
The traditional image processing algorithms used for the location of Chinese chess pieces have high complexity and the traditional character recognition methods used for the recognition of chess pieces have low generalization and accuracy.A segmentation method based on chess piece color features and an improved binary image filtering algorithm are proposed to achieve the fast location of chess pieces,and the second correction of positions is not needed.A recognition method of chess pieces based on a convolutional neural network is proposed,which can be used for the recognition of chess pieces with different fonts.In the case of chess piece replacement,this method can still recognize chess pieces quickly and accurately.The experimental results show that as for the proposed method,the location error is 0.51 mm,the average location time is 0.212 s,and the average recognition accuracy of chess pieces with four types of fonts is about 98.59%.The effectiveness and practicability of this method are confirmed.
引文
[1] Li S G,Yang X L.Design of intelligent line-tracking chess robot based on STM32[J]. Journal of Measurement Science and Instrumentation,2014,5(2):59-63.
[2] Liu F,LüX G.Effects of drug and its packaging on the performance of UHF RFID tag[J].Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition),2017,29(4):563-568.刘飞,吕新广.药品及其包装对超高频RFID标签性能的影响[J].重庆邮电大学学报(自然科学版),2017,29(4):563-568.
[3] Xu F L.The research of the vision algorithm and intelligent control software for chess robot[D].Haerbin:Harbin Institute of Technology,2006:9-13.许丰磊.象棋机器人视觉算法与智能控制软件的研究[D].哈尔滨:哈尔滨工业大学,2006:9-13.
[4] Xiao K X.Research and development of embedded vision system of chess robot[D].Beijing:North China University of Technology,2010:15-26.肖克先.象棋机器人嵌入式视觉系统的研究与开发[D].北京:北方工业大学,2010:15-26.
[5] Du J L,Zhang J F, Huang X H.Chess-board recognition based on vision[J]. Computer Engineering and Applications,2007,43(34):220-222,232.杜俊俐,张景飞,黄心汉.基于视觉的象棋棋盘识别[J].计算机工程与应用,2007,43(34):220-222,232.
[6] Lou L T, Qian L, Duan S,et al. Chessman recognition of Chinese chess based on video image understanding[J]. Journal of South-Central University for Nationalities(Natural Science Edition),2014,33(2):117-122.娄联堂,钱磊,段汕,等.基于视频图像理解的中国象棋棋子识别[J].中南民族大学学报(自然科学版),2014,33(2):117-122.
[7] Wu G,Tao J.Chinese chess recognition algorithm based on computer vision[C]∥China Control and Decision-Making Conference,31 May-2June 2014,Changsha,China.New York:IEEE,2014:3375-3379.
[8] Zhu Y F.Visual recognition algorithm of Chinese chess robot[J].Journal of Jianghan University(Natural Science Edition),2013,41(3):51-56.朱一峰.象棋机器人视觉识别算法研究[J].江汉大学学报(自然科学版),2013,41(3):51-56.
[9] Guo X F,Wang Y N,Zhou X E,et al.Chess-piece localization and recognition method for Chinese chess robot[J].CAAI Transactions on Intelligent Systems,2018,13(4):517-523.郭晓峰,王耀南,周显恩,等.中国象棋机器人棋子定位与识别方法[J].智能系统学报,2018,13(4):517-523.
[10] Zhai N Q.Improved Chinese chessboard recognition method[J].Journal of Computer Applications,2010,30(4):980-981.翟乃强.改进的中国象棋棋盘识别方法[J].计算机应用,2010,30(4):980-981.
[11] Feng Y H,Wang S H,Liu N,et al.Application of machine vision technology in design of chess playing intelligent robot[J]. Computer Engineering and Design,2009,30(14):3371-3373,3379.冯元华,王思华,柳宁,等.机器视觉技术在博弈智能机器人设计中的应用[J].计算机工程与设计,2009,30(14):3371-3373,3379.
[12] Dang H S,Zhang C,Pang Y,et al.Research of fast recognition and positioning system of chess based on ORB algorithm[J]. Science Technology and Engineering,2017,17(7):52-57.党宏社,张超,庞毅,等.基于ORB算法的象棋快速识别和定位系统研究[J].科学技术与工程,2017,17(7):52-57.
[13] Guo J X,Chen W Y.Chesslocation and recognition by screening the feature of polar coordinates projection amplitude[J].Science Technology and Engineering,2018,18(21):268-275.郭建欣,陈文燕.筛选极坐标投影幅值特征的象棋定位与识别[J].科学技术与工程,2018,18(21):268-275.
[14] Wang D J.Recognition andpositioning technique of Chinese chess based on vision[J].Journal of Tsinghua University(Science and Technology),2013,53(8):1145-1149.王殿君.基于视觉的中国象棋棋子识别定位技术[J].清华大学学报(自然科学版),2013,53(8):1145-1149.
[15] Duan Y T,Li Q,Shen W.Chess identification &location in the system of human-machine interaction based on vision[J]. Computer and Digital Engineering,2015,43(8):1416-1418,1485.段云涛,李倩,申玮.基于视觉的人机交互下棋系统中棋子定位及识别技术研究[J].计算机与数字工程,2015,43(8):1416-1418,1485.
[16] Panteley E,Loria A.On global uniform asymptotic stability of nonlinear time-varying systems in cascade[J].Systems &Control Letters,1998,33(2):131-138.
[17] Cao K C,Yang H,Jiang B.Formation tracking control of nonholonomic chained form systems[C]∥2013 10th IEEE International Conference on Control and Automation(ICCA), 12-14 June 2013,Hangzhou,China.New York:IEEE,2013:846-851.
[18] Zhou Y,Dong X W,Lu G,et al.Time-varying formation control for unmanned aerial vehicles with switching interaction topologies[C]∥2014International Conference on Unmanned Aircraft Systems(ICUAS),27-30 May 2014,Orlando,FL,USA.New York:IEEE,2014:1203-1209.
[19] Hua M D,Hamel T,Morin P,et al.Introduction to feedback control of underactuated VTOL vehicles[J].IEEE Control Systems Magazine,2013,33(1):61-75.
[2] Liu F,LüX G.Effects of drug and its packaging on the performance of UHF RFID tag[J].Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition),2017,29(4):563-568.刘飞,吕新广.药品及其包装对超高频RFID标签性能的影响[J].重庆邮电大学学报(自然科学版),2017,29(4):563-568.
[3] Xu F L.The research of the vision algorithm and intelligent control software for chess robot[D].Haerbin:Harbin Institute of Technology,2006:9-13.许丰磊.象棋机器人视觉算法与智能控制软件的研究[D].哈尔滨:哈尔滨工业大学,2006:9-13.
[4] Xiao K X.Research and development of embedded vision system of chess robot[D].Beijing:North China University of Technology,2010:15-26.肖克先.象棋机器人嵌入式视觉系统的研究与开发[D].北京:北方工业大学,2010:15-26.
[5] Du J L,Zhang J F, Huang X H.Chess-board recognition based on vision[J]. Computer Engineering and Applications,2007,43(34):220-222,232.杜俊俐,张景飞,黄心汉.基于视觉的象棋棋盘识别[J].计算机工程与应用,2007,43(34):220-222,232.
[6] Lou L T, Qian L, Duan S,et al. Chessman recognition of Chinese chess based on video image understanding[J]. Journal of South-Central University for Nationalities(Natural Science Edition),2014,33(2):117-122.娄联堂,钱磊,段汕,等.基于视频图像理解的中国象棋棋子识别[J].中南民族大学学报(自然科学版),2014,33(2):117-122.
[7] Wu G,Tao J.Chinese chess recognition algorithm based on computer vision[C]∥China Control and Decision-Making Conference,31 May-2June 2014,Changsha,China.New York:IEEE,2014:3375-3379.
[8] Zhu Y F.Visual recognition algorithm of Chinese chess robot[J].Journal of Jianghan University(Natural Science Edition),2013,41(3):51-56.朱一峰.象棋机器人视觉识别算法研究[J].江汉大学学报(自然科学版),2013,41(3):51-56.
[9] Guo X F,Wang Y N,Zhou X E,et al.Chess-piece localization and recognition method for Chinese chess robot[J].CAAI Transactions on Intelligent Systems,2018,13(4):517-523.郭晓峰,王耀南,周显恩,等.中国象棋机器人棋子定位与识别方法[J].智能系统学报,2018,13(4):517-523.
[10] Zhai N Q.Improved Chinese chessboard recognition method[J].Journal of Computer Applications,2010,30(4):980-981.翟乃强.改进的中国象棋棋盘识别方法[J].计算机应用,2010,30(4):980-981.
[11] Feng Y H,Wang S H,Liu N,et al.Application of machine vision technology in design of chess playing intelligent robot[J]. Computer Engineering and Design,2009,30(14):3371-3373,3379.冯元华,王思华,柳宁,等.机器视觉技术在博弈智能机器人设计中的应用[J].计算机工程与设计,2009,30(14):3371-3373,3379.
[12] Dang H S,Zhang C,Pang Y,et al.Research of fast recognition and positioning system of chess based on ORB algorithm[J]. Science Technology and Engineering,2017,17(7):52-57.党宏社,张超,庞毅,等.基于ORB算法的象棋快速识别和定位系统研究[J].科学技术与工程,2017,17(7):52-57.
[13] Guo J X,Chen W Y.Chesslocation and recognition by screening the feature of polar coordinates projection amplitude[J].Science Technology and Engineering,2018,18(21):268-275.郭建欣,陈文燕.筛选极坐标投影幅值特征的象棋定位与识别[J].科学技术与工程,2018,18(21):268-275.
[14] Wang D J.Recognition andpositioning technique of Chinese chess based on vision[J].Journal of Tsinghua University(Science and Technology),2013,53(8):1145-1149.王殿君.基于视觉的中国象棋棋子识别定位技术[J].清华大学学报(自然科学版),2013,53(8):1145-1149.
[15] Duan Y T,Li Q,Shen W.Chess identification &location in the system of human-machine interaction based on vision[J]. Computer and Digital Engineering,2015,43(8):1416-1418,1485.段云涛,李倩,申玮.基于视觉的人机交互下棋系统中棋子定位及识别技术研究[J].计算机与数字工程,2015,43(8):1416-1418,1485.
[16] Panteley E,Loria A.On global uniform asymptotic stability of nonlinear time-varying systems in cascade[J].Systems &Control Letters,1998,33(2):131-138.
[17] Cao K C,Yang H,Jiang B.Formation tracking control of nonholonomic chained form systems[C]∥2013 10th IEEE International Conference on Control and Automation(ICCA), 12-14 June 2013,Hangzhou,China.New York:IEEE,2013:846-851.
[18] Zhou Y,Dong X W,Lu G,et al.Time-varying formation control for unmanned aerial vehicles with switching interaction topologies[C]∥2014International Conference on Unmanned Aircraft Systems(ICUAS),27-30 May 2014,Orlando,FL,USA.New York:IEEE,2014:1203-1209.
[19] Hua M D,Hamel T,Morin P,et al.Introduction to feedback control of underactuated VTOL vehicles[J].IEEE Control Systems Magazine,2013,33(1):61-75.