摘要
把手写笔迹作为一种纹理来看待,利用图像纹理处理技术和数学方法对笔迹的纹理特征进行提取鉴别,将笔迹识别问题转化为纹理识别。论文使用20个人的不同笔迹进行实验,采用灰度共生矩阵来提取这些笔迹的纹理特征,用夹角余弦相似度算法完成识别工作,取得了较好的效果。
In this paper, we take the handwriting as an image containing some special texture and use the image texture processing technology and mathematical methods, and handwriting identification is regarded as texture identification. We apply gray co-occurrence analytical technique to extract features of such texture and a similarity algorithm to fulfill the identification task. Experiments are made using Chinese handwritings from 20 different people and promising results were achieved.
出处
《信息安全与通信保密》
2006年第6期81-83,共3页
Information Security and Communications Privacy
基金
湖南省教育厅科研项目02C183
关键词
纹理分析
特征提取
笔迹识别
灰度共生矩阵
相似度
texture analysis feature extracting handwriting identification gray co-occurrence similarity
