Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (3): 191-193.DOI: 10.3778/j.issn.1002-8331.2009.03.057

• 图形、图像、模式识别 • Previous Articles     Next Articles

Handwritten signature verification based on contourlet

ZHU Men1,YANG Ming2,LONG Yi3   

  1. 1.College of Electronic Science & Information Technology,Guizhou University,Guiyang 510003,China
    2.School of Information Science & Technology,Southwest Jiaotong University,Chengdu 610031,China
    3.Electrical Engineering Institute,Guizhou University,Guiyang 510003,China
  • Received:2008-01-02 Revised:2008-04-08 Online:2009-01-21 Published:2009-01-21
  • Contact: ZHU Men


朱 门1,杨 明2,龙 奕3   

  1. 1.贵州大学 电子科学与信息技术学院,贵阳 510003
    2.西南交通大学 信息科学与技术学院,成都 610031
    3.贵州大学 电气工程学院,贵阳 510003
  • 通讯作者: 朱 门

Abstract: Handwritten Signature Verification(HSV) is a discipline which aims to validate the identity of writers according to the handwriting styles.Compared with on-line HSV,off-line HSV is less limited in equipment involvement and can be applied in more fields.Nevertheless,it is more difficult to manipulate than on-line HSV due to the loss of dynamic information during the writing process.This paper focuses on off-line HSV and presents a new feature selection method based on Contourlet,which gives full play to the merits of both conventional structure feature and statistical feature.After dimensionality reduction to extracted eigenvector by K-L transform,genuine signatures and forgeries are distinguished through Support Vector Machines(SVM).The result of the experiment has confirmed the effectiveness of the proposed approach.

Key words: Handwritten Signature Verification(HSV), Contourlet, feature extraction, Support Vector Machine(SVM)

摘要: 手写签名验证是一种根据手写笔迹判断书写人身份的一门科学和技术。与联机签名鉴定相比,脱机签名鉴别受设备约束少,具有更广的实用范围。然而,由于脱机签名鉴定丢失了书写过程中的动态信息,鉴定难度大。针对脱机手写签名鉴定的特点,提出了基于Contourlet的特征选取方法,将传统的结构特征与统计特征有机结合起来。运用K-L变换对已提取的特征向量进行降维,最后输入支持向量机进行真伪鉴别。实验结果表明该算法对测试样本具有高识别率。

关键词: 手写签名鉴别, Contourlet, 特征提取, 支持向量机