|
|
Research on Offline Handwritten Chinese Characters RecognitionBased on Biomimetic Recognition |
WANG JianPing1, LI WeiTao1,2,3, WANG JinLing4, WANG XiHui1, CHENG Yu1 |
1.School of Electric Engineering and Automation, Hefei University of Technology, Hefei 2300092. Key Laboratory of Integrated Automation of Process Industry, Ministry of Education, Northeastern University, Shenyang 1100043. Research Center of Automation, Northeastern University, Shenyang 1100044. School of Computer and Information, Hefei University of Technology, Hefei 230009 |
|
|
Abstract In this paper, biomimetic pattern recognition is employed to construct double weighted elliptical neuron sequence which is used to extract basic stroke segments to cover the handwritten Chinese character image. The topological property of the stroke segment neurons is analyzed. An image of handwritten Chinese characters is transformed into geometric figures composed by six styles of Chinese character strokes with fault tolerance. To imitate typing methods of human Chinese characters font code, the style, the number, the position, the number of joint and the crossover of stroke neurons with redundant fault tolerant shapes are counted. Data structures of characteristic knowledge of handwritten Chinese characters are built. Handwritten Chinese characters from SCUTIRAC HCCLIB are tested and the results confirm the proposed method has the ability of cognizing handwritten Chinese characters.
|
Received: 11 September 2006
|
|
|
|
|
[1] Zhang Hui, Zhou Hongxiang, He Zhenya. Extraction of Facial Features for Recognition Based on Principal Component Analysis and Neural Networks. Pattern Recognition and Artificial Intelligence, 1996, 9(1): 5258 (in Chinese) (张 辉,周洪祥,何振亚.基于主元分析神经网络的人脸特征提取及识别研究.模式识别与人工智能, 1996, 9(1): 5258) [2] Lin Shanghuang, Kung S Y, Lin Longji. Face Recognition/Detection by Probabilistic DecisionBased Neural Network. IEEE Trans on Neural Networks, 1997, 8(1): 114132 [3] Intrator N, Reisfeld D, Yeshurun Y. Extraction of Facial Features for Recognition Using Neural Networks // Proc of the International Workshop on Automatic Face and Gesture Recognition. Zurich, Switzerland, 1995: 260265 [4] Zhu Xiaoping, Gu Hongbin. Status of Chinese Characters and Words Recognition. Psychological Science, 1992, 15(1): 4045 (in Chinese) (朱晓平,顾泓彬.汉语字词识别研究的现状.心理科学, 1992, 15(1): 4045) [5] Bian Zhaoqi, Zhang Xuegong. Patern Recognition. 2nd Edition. Beijing, China: Tsinghua University Press, 2000 (in Chinese) (边肇祺,张学工.模式识别.第2版.北京:清华大学出版社, 2000) [6] Yang Sen, Zhang Weilin, Chen Huaimin. Chinese Character Input Code Dictionary of Computer. Hefei, China: USTC Press, 1995 (in Chinese) (杨 森,张伟林,陈怀民.计算机汉字输入编码字典.合肥:中国科学技术大学出版社, 1995) [7] Qian Zituo. Research on Chinese Character Image Recognition. Master Dissertation. Hefei, China: Hefei University of Technology. School of Electrical Engineering and Automation, 2005 (in Chinese) (钱自拓.汉字图像的特征提取与识别研究.硕士学位论文.合肥:合肥工业大学.电气与自动化工程学院, 2005) [8] Wang Shoujue, Xu Jian, Wang Xianbao, et al. MultiCamera HumanFace Personal Identification System Based on the Biomimetic Pattern Recognition. Acta Electronica Sinica, 2003, 31(1): 13 (in Chinese) (王守觉,徐 健,王宪保,等.基于仿生模式识别的多镜头人脸身份确认系统研究.电子学报, 2003, 1(1): 13) [9] Wang Shoujue, Wang Baina. Analysis and Theory of HighDimension Space Geometry for Artificial Neural Networks. Acta Electronica Sinica, 2002, 30(1): 14 (in Chinese) (王守觉,王柏南.人工神经网络的多维空间几何分析及其理论.电子学报, 2002, 30(1): 14) [10] Wang Shoujue, Qu Yanfeng, Li Weijun, et al. Face Recognition: Biomimetic Pattern Recognition vs. Traditional Pattern Recognition. Acta Electronica Sinica, 2004, 32(7): 10571061 (in Chinese) (王守觉,曲延锋,李卫军,等.基于仿生模式识别与传统模式识别的人脸识别效果比较研究.电子学报, 2004, 32(7): 10571061) [11] Lin Fei. Research of Handwritten Chinese Character Recognition. Master Dissertation. Hefei, China: Hefei University of Technology. School of Electrical Engineering and Automation, 2006 (in Chinese) (蔺 菲.手写体汉字识别的研究.硕士学位论文.合肥:合肥工业大学.电气与自动化工程学院, 2006) [12] The New Four Corner Number Dictionary. Beijing, China: Commercial Press, 2002 (in Chinese) (四角号码新字典.北京:商务印书馆, 2002) |
|
|
|