摘要
目前,手写体字符识别领域在所包括的特征提取、识别器、合成器等方方面面已经形成了两大类识别方法:基于结构特征的方法和基于统计特征的方法。本文旨在描述和评价这些问题的精要所在,并结合我们自己在这方面的工作对该领域的发展方向和前沿课题提出一些看法。
Handwritten Character Recognition is an important area in pattern recognition. During the 1990s, lots of researches result in commercial systems. There are two basic trends in this field, which is structural approach and statistical approach, concerning feature extraction, classifier, and combination. Years of researches provide the authors with profound insight into the essence of this problem. In this paper we try to direct the way to the frontier of this field.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2000年第2期174-180,共7页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金
国家重点基础研究规划资助项目
关键词
特征提取
手写体字符识别
汉字信息处理
Character Recognition, Feature Extraction, Classifier, System Combination
