有限集手写汉字识别中的笔画分区矩描述特征  

Small Set Handwritten Chinese Character Recognition Using Stroke Partition Moment Features

作　　者：居琰[1] 汪同庆[1] 刘建胜[1] 王贵新[1] 袁祥辉[1] 

机构地区：[1]重庆大学光电工程学院,重庆400044

出　　处：《计算机工程》2003年第7期15-16,168,共3页Computer Engineering

摘　　要：提出了一种笔画分区矩特征的提取方法。根据汉字笔画分布特点，利用小波变换将汉字分解为4个方向笔画分量，用分区矩分别描述4个笔画子图像，并采用K-L变换对特征进行降维处理。采用该特征对有限集手写体汉字进行识别，初步实验结果表明该方法十分有效。This paper proposes a feature extraction method based on partition moments and stroke decomposition. According to stroke distributing characteristic of Chinese character, a character image is decomposed into four directional sub images using the wavelet transform. Then, partition moment features are extracted from the four sub-images respectively. After dimensions reduction of original feature using Karhunen-Loeve transform, the feature is used for small set handwritten Chinese character recognition. The result of experiment shows high recognition rate which indicates that the method is very effective.

关 键 词：矩 笔画分解 特征提取 手写汉字识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]