首页 | 本学科首页   官方微博 | 高级检索  
     

基于纹理的文本依存的离线笔迹鉴别
引用本文:于明,苗晓峰,范书瑞. 基于纹理的文本依存的离线笔迹鉴别[J]. 河北工业大学学报, 2007, 36(5): 95-100
作者姓名:于明  苗晓峰  范书瑞
作者单位:河北工业大学,计算机科学与软件学院,天津,300401;河北工业大学,计算机科学与软件学院,天津,300401;河北工业大学,计算机科学与软件学院,天津,300401
摘    要:针对文本依存的离线笔迹鉴别,提出一种基于纹理的算法.该算法采用Gabor变换对纹理进行分析,选取4个频率8个相位,通过变换,选取32维变换系数的方差作为笔迹特征,在分类时使用欧氏距离作为分类器,并且提出一种新的阈值获取方法,针对该算法进行实验得出,正确接受率为89.3%,正确拒绝率为80.0%.

关 键 词:文本依存  纹理  笔迹鉴别  离线  特征提取  分类器
文章编号:1007-2373(2007)05-0095-06
修稿时间:2007-01-16

Off-line Handwriting Verification of Context Dependent Based on Texture
YU Ming,MIAO Xiao-feng,FAN Shu-rui. Off-line Handwriting Verification of Context Dependent Based on Texture[J]. Journal of Hebei University of Technology, 2007, 36(5): 95-100
Authors:YU Ming  MIAO Xiao-feng  FAN Shu-rui
Affiliation:School of Computer Science and Software, Hebei University of Technology, Tianjin 300401, China
Abstract:This paper presents a context dependent method of off-line handwriting verification based on the texture feature.Gabor filter is used in the texture analysis to gain handwriting features.By choosing 4 frequencies and 8 directions,it will get 32 Gabor coefficients,and this paper chooses the variance of coefficients as handwriting feature.The Euclidean distance is applied as classifier,and a new technique for getting threshold value is proposed in this paper.Experimental results show that the correct acceptances rate is 89.3% and the correct rejections rate is 80.0%.
Keywords:context dependent  texture  handwriting verification  off-line  feature extraction  classifier
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号