摘要
基于现有的藏文字丁特征提取方法——图像投影法和方向线素法,运用分形矩理论,提出了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地反映了藏文字丁的局部和全局特征,减少了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了藏文字丁极多而造成的误识率高的缺点,并且解决了由于特征向量维数较多造成的运算速度慢的问题.
A feature extraction approach for printed Tibetan character based on fractal moments is proposed. After analyzing present feature extraction approaches image projection approach and directional line element approach, the fractal moments theory is applied in the proposed approach. The extracted features using the new method can describe the local and global properties of the character, and decreases the adverse effect which is brought to recognition part by the change of pixel＇s position in the image. The method can not only overcome high probability＂ of misrecognition due to numerous Tibetan characters, but also solve the low arithmetic speed owing to plenty feature vector dimensions.
出处
《江南大学学报（自然科学版）》
CAS
2007年第6期791-794,共4页
Joural of Jiangnan University (Natural Science Edition)
基金
江苏省高校自然科学基金项目(2005DX006J)
江苏科技大学科研基金项目
关键词
藏文字符识别
分形矩
特征提取
tibetan character recognition
fractal moments
feature extraction
