A feature extraction approach for printed Tibetan character based on fractal moments is proposed. After analyzing the existing feature extraction approaches, the image projection approach and the directional line element approach, the fractal moments theory is applied in the proposed approach. The extracted features using the proposed method can describe the local and global properties of the character, and decrease the adverse influence caused by the change of pixel position in the image. The method can overcome high probability of misrecognition of numerous Tibetan characters, and solve the low arithmetic speed problem caused by more feature vector dimensions. Experimental results on 592 categories of printed Tibetan characters show the effectiveness of the proposed method. Moreover, the recognition rate of the proposed approach is about 2.48% higher than that of any other existing feature extraction approach.
刘真真,王茂基,李永忠,沈晔华. 基于分形矩的印刷体藏文特征提取方法[J]. 模式识别与人工智能, 2008, 21(5): 654-657.
LIU Zhen-Zhen, WANG Mao-Ji, LI Yong-Zhong, SHEN Ye-Hua. Feature Extraction Approach for Printed Tibetan Character Based on Fractal Moments. , 2008, 21(5): 654-657.
[1] Wang Weilan. Algorithm Study on Feature Extracting of Tibetan Character Recognition. Journal of Northwest University for Nationalities: Natural Science, 1999, 20(3): 20-23, 51 (in Chinese) (王维兰.藏文基本字符识别算法研究.西北民族大学学报:自然科学版, 1999, 20(3): 20-23, 51) [2] Kato N, Suzuki M, Omachi S, et al. A Handwritten Character Recognition System Using Directional Element Feature and Asymmetric Mahalanobis Distance. IEEE Trans on Pattern Analysis and Machine Intelligence, 1999, 21(3): 258-262 [3] Wang Hua, Ding Xiaoqing. Multi-Font Printed Tibetan Character Recognition. Journal of Chinese Information Processing, 2003, 17(6): 47-52 (in Chinese) (王 华,丁晓青.多字体印刷藏文字符识别.中文信息学报, 2003, 17(6): 47-52) [4] Swarnakar V. Accurate Fractal Dimension Estimation and Its Application to Image Analysis. Ph.D Dissertation. New York, USA: State University of New York at Buffalo, 1998: 40-55 [5] Liao S X, Pawlak M. On Image Analysis by Moments. IEEE Trans on Pattern Analysis and Machine Intelligence, 1996, 18(3): 254-266 [6] Faugeras O D, Pratt W K. Decorrelation Methods of Texture Feature Extraction. IEEE Trans on Pattern Analysis and Machine Intelligence, 1980, 2(1): 323-332 [7] Prokop R J, Reeves A P. A Survey of Moment-Based Techniques for Unoccluded Object Representation and Recognition. CVGIP: Graphical Models and Image Processing, 1992, 54(5): 438-460 [8] Hu M K. Visual Pattern Recognition by Moment Invariants. IEEE Trans on Information Theory, 1962, 8(1): 179-187 [9] Wang Hua, Ding Xiaoqing. A Normalization Method of Multi-Font Printed Tibetan Characters. Application Research of Computers, 2004, 21(6): 41-43 (in Chinese) (王 华,丁晓青.一种多字体印刷藏文字符的归一化方法.计算机应用研究, 2004, 21(6): 41-43) [10] Brown G, Michon G, Peyriere J. On the Multifractal Analysis of Measures. Journal of Statistical Physics, 1992, 66(3/4): 775-790