期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2010
卷号：10
期号：5
页码：29-35
出版社：International Journal of Computer Science and Network Security
摘要：This paper presents a novel off-line signature identification method based on Fourier Descriptor ( FDs ) and Chain Codes features. Signature identification classified into two different problems: recognition and verification. In recognition process we used Principle Component Analysis. In verification process we designed a multilayer feed forward artificial neural network. The main steps of constructing a signature identification system are discussed and experiments on real data sets show that the average error rate can reach 3.8%.
关键词：signature recognition; Fourier Descriptor; Principle Component Analysis; personal verification
Loading...
