首页 | 本学科首页   官方微博 | 高级检索  
     

基于小波包分析的在线手写签名认证方法
引用本文:马海豹,刘漫丹,张岑. 基于小波包分析的在线手写签名认证方法[J]. 计算机工程与应用, 2007, 43(12): 235-238
作者姓名:马海豹  刘漫丹  张岑
作者单位:华东理工大学,自动化研究所,上海,200237
摘    要:针对在线手写签名难以提取有效特征的实际情况,提出用小波包分解和单支重构来构造能量特征向量的方法,直接利用各频段成分能量的变化来反映签名的动态特征。用该方法构造的特征向量能突出反映签名的动态特征,通过RBF神经网络进行签名识别。实验数据表明,采用此方法,识别的正确率可达96.75%,平均错误率ERR=3.34%,其性能是较满意的。

关 键 词:手写签名认证  小波包分析  特征提取  RBF神经网络
文章编号:1002-8331(2007)12-0235-04
修稿时间:2006-08-01

New method of on-line handwritten signature verification based on wavelet packet analysis
MA Hai-bao,LIU Man-dan,ZHANG Cen. New method of on-line handwritten signature verification based on wavelet packet analysis[J]. Computer Engineering and Applications, 2007, 43(12): 235-238
Authors:MA Hai-bao  LIU Man-dan  ZHANG Cen
Affiliation:Inst. of Automation,East China Univ. of Sci. and Tech.,Shanghai 200237,China
Abstract:It is difficult to extract the effective features of on-line signature verification,so a new method of dynamic feature extraction is proposed by decomposition and reconstruction of wavelet packet in this paper.The feature vectors that reflect the energy change of different frequency ranges are constructed by the method and the feature vectors can reflect the dynamic feature of signature effectively.Moreover,RBF neural network is used to recognize signature by the feature vectors constructed above.Experiment shows that recognition is correct to 96.75% and equal error rate is 3.34%.The performance is satisfactory.
Keywords:handwritten signature verification  wavelet packet analysis  feature extracfion  RBF neural network
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