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。本文针对脱机手写签名鉴定的特点,提出了基于Contourlet和分形维的特征选取方法,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。实验结果表明了本文算法的高识别性。
Handwritten signature verification （HSV） is a discipline that aims to validate the identity of writers according to the handwriting styles. Compared with on-line HSVs, off-line HSVs are less restricted by the equipment involved and can be applied in more fields, but more difficult to manipulate due to the loss of dynamic writing information such as writing position, velocity, acceleration and pressure. In this paper, we focus on off-line HSV and present a new feature extraction method based on Contourlet and fractal dimension, which gives full play to the merits of both conventional structure feature and statistical feature. After dimensionality reduction to extract eigenvector by K-L transform, genuine signatures and forgeries are distinguished through support vector machine （SVM）. Experiment results confirm the effectiveness of the proposed system.
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2007年第10期1751-1758,共8页
Chinese Journal of Scientific Instrument
基金
Supported by Hong Kong Special Administrative Region(CUHK 4163/03E)
Ministry of Science and Technology,The People's Republic of China(International S&T Cooperation Projects 2006DFB73360)
National Natural Science Foundation of China(60602043)
