刘伟,朱宁波,何浩智,李德鑫,孙发军. 基于弹性网格模糊特征的手写体汉字识别方法[J]. 中文信息学报, 2007, 21(3): 117-121.
LIU Wei, ZHU Ning-bo, HE Hao-zhi, LI De-xin,SUN Fa-jun. A Feature Extracting Method for Handwritten Chinese Character Recognition Based on Elastic Mesh and Fuzzy Feature of Block. , 2007, 21(3): 117-121.
基于弹性网格模糊特征的手写体汉字识别方法
刘伟,朱宁波,何浩智,李德鑫,孙发军
湖南大学 计算机与通信学院,湖南 长沙410082
A Feature Extracting Method for Handwritten Chinese Character Recognition Based on Elastic Mesh and Fuzzy Feature of Block
LIU Wei, ZHU Ning-bo, HE Hao-zhi, LI De-xin,SUN Fa-jun
Computer and Communication College, Hunan University, Changsha,Hunan 410082, China
Abstract：The directional feature is considered suitable for handwriten chinese character recognition,and it has been widely used as one of the main feature extraction method.Meshing method is one of the key factors of meshing direction feature.According to stroke distributing characterisitic and topologic correlation of chinese characters,we present a new method based on elastic mesh and related fuzzy feature.A more stable feature vector with more information is extracted. The experiment based on the handwritten legal amount on Chinese bank check shows that the method is more effective than other meshing direction features,and recognition rate has been up to 97.64%.
:[1] Qivind Due Trier,et al.Feature Extraction Methods for Character Recognition:A Survey[J].Pattern Recogniton,1996,29(4):641-662. [2] R Plamondon,S N Srihari.On-line and Off-line Handwritting Recogition:A Comprehensive Survey[J].IEEE Trans on PAMI,2000,22(1):63-81. [3] 陈津颖,金奕江,马少平.手写体汉字在特征空间的可视化分析[J].中文信息报,2000,14(5):42-48. [4] 王正群,叶晖,孙兴华,杨静宇.基于模糊方向特征的手写体汉字识别[J].模式识别与人工智能,2001,9(3):318-320. [5] 马少平,夏莹,朱小燕.基于模糊方向线素特征的手写体汉字识别[J].清华大学学报(自然科学版),1997,37(3):42-45. [6] 吴天雷,马少平.基于重叠动态网格和模糊隶属度的手写体汉字特征抽取[J].电子学报,2004,2:187-190. [7] 孙立民,狄红卫,余英林.基于子块特征及其相关模糊隶属度特征的手写体汉字识别方法[J].通信学报,1999,20(12):82-85. [8] 王正群.手写体汉字识别研究[D].南京:南京理工大学计算机系,2001. [9] 边肇祺.模式识别[M].北京:清华大学出版社,1998.
2007, Vol. 21 
