Title :
An Improved Method for Similar Handwritten Chinese Character Recognition
Author :
Yang, Fang ; Tian, Xue-dong ; Zhang, Xin ; Jia, Xin-Biao
Author_Institution :
Coll. of Math. & Comput. Sci., Hebei Univ., Baoding, China
Abstract :
Similar characters existed in Chinese character affect much on enhancing the handwritten Chinese character recognition rate. An improved method is presented in this paper, which combines structural and statistical features for similar handwritten Chinese character recognition,. Four-corner code feature that based on stroke structure is used to get the similar character set. According to the different strokes on the four corners, four-corner code feature can dispatch some characters which are similar in shape into different similar sets. Statistical hierarchy contour features are extracted from the characters in the same similar set, then support vector machine (SVM) is adopted as classifier to recognize the similar characters. This method reduces the complexity of recognizing similar characters, and the experiment results on common used 500 Chinese characters show the effectiveness.
Keywords :
computational complexity; feature extraction; handwritten character recognition; statistical analysis; support vector machines; SVM; four-corner code feature; similar handwritten Chinese character recognition; statistical hierarchy contour feature extraction; structural-statistical features; support vector machine; Character recognition; Competitive intelligence; Computational intelligence; Feature extraction; Hidden Markov models; Information technology; Learning systems; Shape; Support vector machine classification; Support vector machines; Four-corner code feature; SVM; hierarchy contour feature; similar character recognition;
Conference_Titel :
Intelligent Information Technology and Security Informatics (IITSI), 2010 Third International Symposium on
Conference_Location :
Jinggangshan
Print_ISBN :
978-1-4244-6730-3
Electronic_ISBN :
978-1-4244-6743-3
DOI :
10.1109/IITSI.2010.70
