几种手写体汉字网格方向特征提取法的比较研究  

Study of Several Handwritten Chinese Character Directional Feature Extraction Approaches

作　　者：金连文[1] 高学[1] 

机构地区：[1]华南理工大学电子信息学院,广东广州510641

出　　处：《计算机应用研究》2004年第11期38-40,90,共4页Application Research of Computers

基　　金：国家自然科学基金资助项目(60275005);广东省自然科学基金资助项目(011611)

摘　　要：近年来,网格方向特征已广泛应用于许多手写体汉字识别系统中,并认为是目前较成熟的手写体汉字特征之一。网格技术和方向分解是网格方向特征的两个关键技术。方向特征提取方法有许多种并各有优劣。对几种方向特征提取方法进行了比较研究,对其中一些方法进行了改进,并将我们提出的局部网格的划分方法应用到这几种方向分解特征的提取上,取得了较好的识别效果。Recently,it is found that the directional feature is considered suitable for Chinese character recognition,and directional feature has been widely used as one of the mainstream feature extraction approach.Directional decomposition algorithm and meshing method are two key factors in extraction of directional feature.This paper presents several directional features with different meshing methods for Handwritten Chinese Character Recognition (HCCR).Local elastic meshing technology is introduced in this paper,and it is found that local elastic meshing method is much better than global elastic meshing method.

关 键 词：特征提取 手写体汉字识别 局部弹性网格 方向特征 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]