基于纹理分析的笔迹识别系统  

Handwriting Identification System Based on Texture Analysis

作　　者：杨子华[1] 吴敏[2] 凌江荣[1] 

机构地区：[1]湖南工程学院计算机科学系,湖南湘潭411101 [2]中南大学信息科学与工程学院,湖南长沙410082

出　　处：《湖南工程学院学报（自然科学版）》2004年第2期67-69,共3页Journal of Hunan Institute of Engineering(Natural Science Edition)

摘　　要：把手写笔迹作为一种纹理来看待,利用图象纹理处理技术和数学方法对笔迹的纹理信息进行鉴别,将笔迹识别问题转化为纹理识别.使用19个人的不同笔迹进行实验,采用游程长度分析法来提取这些笔迹的纹理特征,用欧氏距离分类器完成识别工作.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 to identify the handwriting texture,Handwriting identification is regarded as texture identification.We use distance covered length analytical technique to extract features of such texture and a Euclidean Distance classifier to fulfill the identification task.Experiments are made by using Chinese handwritings from 19 different people and promising results are achieved.

关 键 词：纹理分析 笔迹识别 游程长度 欧氏距离分类器 

分 类 号：TP391.12[自动化与计算机技术—计算机应用技术]