摘要
生物特征识别技术作为一种身份识别的手段,具有独特的优势,近年来已逐渐成为国际上的研究热点.签名认证属于生物特征识别技术的一种,已经在国内外各个领域应用数十年,被人们广泛接受.对现有的离线签名认证方法进行了改进和创新,提出了四种特征,包括方向特征、纹理特征、动态特征和复杂指数.认证阶段采用支持向量机来鉴定签名的真伪,所取得的最好实验结果是平均错误率达到了5.4%,和目前国内外离线签名认证的相关实验结果相比,说明了本实验算法的有效性.
Handwritten signature is one of the most widely accepted personal attributes for identity verification. As a symbol of consent and authorization, handwritten signature has long been the target of fraudulence. We put forward four novel features including direction features, texture features, dynamic features and the complexity index. The experiment results show that adopting SVM classifier to verify the signatures can get good effects. The signature verification system was experimented on real data sets and the results show that the system is effective with the average error rate of 5.4%.
出处
《兰州工业高等专科学校学报》
2009年第4期8-12,共5页
Journal of Lanzhou Higher Polytechnical College
作者简介
曾晓云（1981-），女，湖北钟祥人，硕士．
