Dynamic algorithms for identifying unique features from a person's handwritten signature
Abstract
Dynamic algorithms for identifying unique features from a person's handwritten signature
Incoming article date: 13.02.2024Currently, to access information contained in autonomous and external information systems, user must pass an authorization process using modern methods of identity verification, such as: password protection, protection based on one-time codes, electronic signature-based protection, etc. These methods as always have worked well and still continue to provide secure access, however, biometric authentication methods are more reliable when access to confidential information should be limited to a single user. Today, there are two types of biometric authentication methods: static and dynamic. Static methods based on a person's biological characteristics that remain with them throughout their life, while dynamic methods based on a person's behavioral characteristics. Static methods are considered some of the most accurate, because most biometric parameters do not change over a lifetime. However, this method should only be used if chance of data compromise is very low, because in the event of leak, user will not be able to continue using these types of methods anywhere else. Dynamic methods, due to their behavioral characteristics, do not have sufficiently satisfactory type I and II error rates, as they directly depend on user's psychological and physical state. However, unlike static methods, user can control the information that will serve as a secret key for authorization in the future, so in case of a leak, user can always change the contents of the key for current and future services. This work examines one of these dynamic methods of biometric authentication: verification by handwritten signature. This method is considered more attractive among its counterparts, as in case of successful type I and II error rates, it can be applied in most existing services as a tool for authentication and confirmation of user intentions when signing various types of documents. The article discusses the main algorithms for verifying handwritten signatures by identifying unique dynamic features, dependent on the temporal and coordinate values of the analyzed samples of handwritten signatures.
Keywords: dynamic algorithms, feature extraction, signature writing time, proximity of point coordinate functions, Fourier transform