首页 | 本学科首页   官方微博 | 高级检索  
     

基于局部轮廓方向特征的笔迹鉴别
引用本文:丁红,吴辉群,张晓峰.基于局部轮廓方向特征的笔迹鉴别[J].电视技术,2013,37(23).
作者姓名:丁红  吴辉群  张晓峰
作者单位:南通大学,南通大学,南通大学
基金项目:国家自然科学基金(61170171);南通市科技计划项目(BK2011011)
摘    要:作为一种安全可靠的生物识别技术,笔迹鉴别在模式识别领域中获得了广泛的关注。本文利用局部结构的概率分布能够体现笔迹特征的思想,提出一种基于局部轮廓方向特征的离线笔迹鉴别方法。使用和窗口中心连通的边缘片段减少笔迹粗细的影响,将边缘点分成32种方向类别从而获取辨别局部轮廓的能力。在此基础上,统计以边缘点为中心的滑动窗口中的方向特征并归一化为局部轮廓方向特征。最后,使用加权Manhattan距离对笔迹特征进行相似性度量。实验表明提出的方法在ICDAR2011笔迹鉴别竞赛的多语言测试数据库上获得了较好的辨别正确率,部分指标超过了目前的先进算法。

关 键 词:笔迹鉴别  笔画特征  局部轮廓方向特征  加权Manhattan距离
收稿时间:2013/6/28 0:00:00
修稿时间:2013/6/28 0:00:00

Writer Identification based on Local Contour Direction Features
Ding Hong,Wu Hui Qun and Zhang Xiao Feng.Writer Identification based on Local Contour Direction Features[J].Tv Engineering,2013,37(23).
Authors:Ding Hong  Wu Hui Qun and Zhang Xiao Feng
Affiliation:Nantong University,Nantong University,Nantong University
Abstract:Writer identification, which is a secret and reliable biometric technology, has attractted widespread attantion in partten recognition field. The distribution of local structures can be used as the feature of handwriting. Using this idea, a method based on local contour direction feature is proposed for off-line writer indentifaction in this paper. It reduces the inpact of stroke wideth by ignoring the fragments which do not directly connect the center point. The edge points are divided into 32 catigories to gain the directions of local fragments. This method counts the direction features in sliding windows and normalizes them into local contour direction features. The weighted Manhattan distance is used as similarity measurement at last. The experiments on ICDAR 2011 writer identification database with multi-languages show that the performances of the proposed method reach or exceed the state-of-art methods.
Keywords:writer identification  stroke feature  local contour direction feature  weighted Manhattan distance
点击此处可从《电视技术》浏览原始摘要信息
点击此处可从《电视技术》下载全文
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