An Online Handwritten Signature Authentication Method Based on Dynamic Threshold

Abstract

The invention is an online handwritten signature authentication method based on a dynamic threshold, which belongs to the field of information security. The method of the invention comprehensively models the coordinates, pressure, and speed information of the online signature, and then comprehensively considers the effects of various factors to more effectively improve the Accuracy rate of signature judgment; the method of the present invention adopts the strategy of segmentation discrimination to signature, and according to the writing habit of the signer, automatically selects the relatively stable segmentation method in two segmentation strategies, thereby can improve signature in the signature judgment process. The accuracy of the similarity judgment; the threshold value used in the signature judgment process of the method of the present invention is dynamically determined according to different signatures, which is conducive to reflecting the deviation characteristics of each signature, that is, taking into account the characteristic stability of each signature Different questions to get the best comparison for each.

Description

technical field [0001] The invention belongs to the field of information security, and in particular relates to an online handwritten signature authentication method based on a dynamic threshold. Background technique [0002] In today's society, with the rapid development of computer technology and Internet technology, the information revolution has had a huge impact on people's traditional office and lifestyle, and information security has become one of the focal issues that people face. Applications such as e-commerce, online transactions, online payment, and network file transfers have more prominent requirements for information security, and accurate and fast identity authentication has become an urgent need. Identity authentication methods can be divided into several common categories: knowledge-based methods, such as system passwords, passwords, etc.; token-based methods, such as ID cards, IC cards, etc.; , handwritten signature, etc. Among the identification methods...

AI Technical Summary

Problems solved by technology

In the existing online handwritten signature system, the authenticity of the handwritten signature is judged based on the similarity comparison between the feature quantity of each written signature and the real signature feature quantity of the sample database, and in the process of similarity comparison, Both use a fixed threshold, thus ignoring the deviation characteristics of each person's signature, that is, ignoring the problem that the stability of each person's signature is different, so that the best comparison result for each person cannot be obtained

Images