期刊名称:International Journal of Computer Trends and Technology
电子版ISSN:2231-2803
出版年度:2012
卷号:3
期号:3-1
出版社:Seventh Sense Research Group
摘要:Today signature verification are used in various places for authentication and security purpose .Every signature or signed identified each person physiological or behavioral characteristic. Signature matching is very important in this time because any person can generated another person signature in fraud way. So systems have need for verification of the signature. The signature verification can be done either offline or online signature matching techniques and in this paper we apply offline signature matching technique. Here we propose an intelligent neural network that work on the feature like pixel density method, directional method and mix both method together .and compared both the result and which of the best. Which Accuracy, Performance, FAR, FRR are best.
关键词:Neural Network; FRR; FAR; pixel density method; directional method