基于笔划特征的单字符汉字字体识别  

FONT RECOGNITION OF SINGLE CHINESE CHARACTER USING STROKE FEATURES

作　　者：陈力[1] 丁晓青[1] 

机构地区：[1]清华大学电子工程系,北京100084

出　　处：《模式识别与人工智能》2004年第2期212-217,共6页Pattern Recognition and Artificial Intelligence

摘　　要：在文档电子化的文本自动分析、理解和识别过程中,除了有关文档内容的字符识别外,还必须解决字体识别问题.字体识别不仅是版面分析、理解和恢复的重要依据,还有助于实现高性能字符识别系统.有别于目前基于多个字符组成的文本块的字体识别方法,本文提出了一种基于单个汉字字符的字体识别方法.在单个汉字字符上提取两类特征:笔划属性特征和笔划分布特征,分别构成两个分类器对单个汉字字符进行字体识别,并集成两个分类器的结果得到最终的识别结果.我们使用的笔划属性特征分类器是文本无关的,而笔划分布特征分类器是文本相关的,集成的分类器属于文本相关的字体识别分类器.我们在包含7种字体的样本集上进行了测试,测试结果显示基于单字的字体识别率达到94.48%.Printed character image includes not only the information of characters, but also the information of fonts. Font information is helpful in layout analysis and reconstruction, and is helpful to improve the performance of character recognition system. An algorithm for font recognition of single Chinese character is proposed in this paper. The aim is to analyze a single Chinese character and to identify the font. The new algorithm can recognize the font of a single Chinese character while existing methods are all based on a block of text. Stroke property features and stroke distribution features are extracted from a single Chinese character and two classifiers are employed using these features to classify different fonts. We combine these two classifiers to get the final result of font recognition. Experiment shows that our method can recognize the font of single Chinese character effectively and an accuracy rate of 94. 48% is achieved.

关 键 词：字体识别 单字符 笔划属性特征 笔划分布特征 

分 类 号：TP391.43[自动化与计算机技术—计算机应用技术]