Research on online signature verification based on anomaly detection

Abstract

With the advancement of modern information technology, personal information security has become the focus of social attention. As a biological behavior feature, online signatures have been trained for a long time, have very personal characteristics, and are collected as a real-time sequence. In view of this characteristic, we can know that it is difficult for forgers to imitate the intrinsic and essential characteristics of the signer. In addition, a signature is a rapid writing process driven by the central nervous system and personal writing habits. Even the signer himself may write an unstable and similar forgery signature, so it is necessary to analyze the variability and stability of signatures. Therefore, this paper proposes a method of using the variance and characteristics of local features to find a stable segment of the user’s signature for authentication. In addition, we also adopt a two-stage authentication strategy that combines the above method with the traditional anomaly detection algorithm. An experiment was conducted on the open-access online signature database MCYT, and an EER of 2.63% was obtained. The experiment proved the effectiveness and robustness of the method.