期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2015
卷号：4
期号：4
页码：1448-1451
出版社：Shri Pannalal Research Institute of Technolgy
摘要：In this paper, we present a system using a set of time sequences and Hidden Markov Models (HMMs) to verify the online signatures. The signature is added to computer by the digital pen includes the following information: position trajectories, pressures and tilts of the pen. With the signature obtained, our system will extract 20 features in each points of the signature, andthe system will standardize these features before they enter into the system for training or testing. This standardization aims to enhance the accuracy of the system. When conducting authentication, a user's signature is considered to be correct when the similarity measure calculated by the system on which the signature is greater than a threshold. We have compared our system with other systems: the systems of competition authenticate Signatures First International (SVC2004) [6], the Lei system [5]. In the process of building the system, we have conducted several experiments to find out the specific effect of the signature and the optimal parameters for hidden Markov models.
