An improved method for the character recognition based on SVM

To deal with the character recognition in Chinese vehicle license plate, several feature extraction algorithms are compared in this paper, as well as their performance based on the SVM classifier and the conventional MDC classifier, respectively. The result shows that the combination of Gabor feature and SVM classifier can reach good performance, especially for the Chinese character recognition.

[1]  Jin Hyung Kim,et al.  High accuracy handwritten Chinese character recognition by improved feature matching method , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.

[2]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[3]  Anil K. Jain,et al.  Feature extraction methods for character recognition-A survey , 1996, Pattern Recognit..

[4]  Qin Lu,et al.  Chinese character recognition via Gegenbauer moments , 2002, Object recognition supported by user interaction for service robots.

[5]  Jingping Jiang,et al.  An adaptive approach to vehicle license plate localization , 2003, IECON'03. 29th Annual Conference of the IEEE Industrial Electronics Society (IEEE Cat. No.03CH37468).

[6]  Yon-Ping Chen,et al.  Robust license plate recognition based on dynamic projection warping , 2004, IEEE International Conference on Networking, Sensing and Control, 2004.

[7]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.