论文信息 - A Novel Character Recognition Algorithm Based on Hidden Markov Models

A Novel Character Recognition Algorithm Based on Hidden Markov Models

In this paper, a novel character recognition algorithm based on the Hidden Markov Models is proposed. Several typical character features are extracted from every character being recognized. A novel 1D multiple Hidden Markov models is constructed based on the features to recognize characters. A large number of vehicle license plate characters are used to test the performance of the algorithm. Experimental results prove that the recognition rate of this algorithm is high aiming at different kinds of character.

Lei Han | Yu Wang | Xueye Wei | Xiaojin Wu

[1] Sameh M. Awaidah,et al. A multiple feature/resolution scheme to Arabic (Indian) numerals recognition using hidden Markov models , 2009, Signal Process..

[2] Daming Shi,et al. Handwritten Chinese Radical Recognition Using Nonlinear Active Shape Models , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[3] Zhang Hong. Application of HMM in Handwritten Digit OCR , 2003 .

[4] Lawrence R. Rabiner,et al. A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[5] D. W. Tindall. Application of neural network techniques to automatic licence plate recognition , 1995 .

[6] Zhang Yin. 2D HMM BASED CHARACTER RECOGNITION OF THE ENGINEERING DRAWING , 1999 .

[7] Yang Qing-xiong. Realization of character recognition based on neural network , 2005 .

[8] Jie Li,et al. A new approach for off-line handwritten Chinese character recognition using self-adaptive HMM , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

[9] Long Jian-zhong. Independent Component Analysis Based on Licence Plate Recognition , 2006 .