摘要
提出了一种基于汉字结构关系的手写汉字识到粗分类的新方法。该方法以抽取手写汉字基本笔划为基础，利用汉字的结构特征进行粗分类。它不仅算法简单、分类速度快、分类能力强、分类稳定、可靠，而且在分类的同时又能把组成汉字的部件及其笔划随之而分离出来，为用句法结构方法识别手写汉字奠定了基础。这种方法成功地用于在ＰＣ／ＡＴ机上实现的成页手写体（楷书）汉字识别系统中，效果满意。
A new preliminary classification method based on the structural relation of Chinese characters for handprinted Chinese character recognition is presented. The method is based on the extraction strokes of handprinted Chinese characters and makes use of information of the strokes' terminal coordinates to classify handprinted Chinese characters according to its structural relation. It is characterized not only by a simple algorithm and a powerful, fast, stable and reliable classification. but also seperates the components of the Chinese characters while they are being classified. It can build a strong foundation for Chinese character recognition by syntax structural method. Now,it has been successfully used in handprinted Chinese character system based on PC/AT computer with satisfactory results.
出处
《电子科技大学学报》
EI
CAS
CSCD
北大核心
1996年第3期311-315,共5页
Journal of University of Electronic Science and Technology of China
基金
电子部预研基金
关键词
特征提取
汉字分类
汉字识别
手写体
计算机应用
feature extraction
Chinese character classification
Chinese character recognition
handprinted
