基于分形矩的印刷体藏文特征提取方法  

Feature Extraction Approach for Printed Tibetan Character Based on Fractal Moments

作　　者：刘真真[1] 王茂基[1] 李永忠[1] 沈晔华[1] 

机构地区：[1]江苏科技大学电子信息学院,镇江212003

出　　处：《模式识别与人工智能》2008年第5期654-657,共4页Pattern Recognition and Artificial Intelligence

摘　　要：在分析现有的藏文字丁特征提取方法——图像投影法和方向线索法的基础上,运用分形矩理论,提出一种基于分形矩的藏文字符特征提取方法.用该方法提取的特征有效反映藏文字丁的局部和全局特征,减少图像中像素位置变化给识别部分带来的负面影响.该方法在一定程度上克服藏文字丁极多而造成的误识率高的缺点,并且解决由于特征向量维数较多造成的运算速度慢的问题.针对592个类别的印刷体藏文字丁样本的对比实验表明,本文方法的识别率较现有的特征提取方法平均增加了2.48%,证明此方法具有较好的特征提取性能.A feature extraction approach for printed Tibetan character based on fraetal 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.

关 键 词：藏文字符识别 特征提取 分形矩 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]