Biological feature adaptive learning identification method and system

Abstract

The embodiment of the invention provides a biometric feature adaptive learning identification method. The method comprises steps of taking the biological characteristics of a user collected during registration as basic characteristics, and storing the basic characteristics into a biological characteristic template; in the process of collecting the biological characteristics of the user to carry out first identity authentication, if second identity authentication is triggered, carrying out identity marking on the biological characteristics by utilizing an authentication result of the second identity authentication; adding the biological characteristics with the marks to a self-adaptive learning template; and carrying out biometric feature recognition on the user by utilizing the biometric feature template and the adaptive learning template which are independent of each other. The embodiment of the invention further provides an identification system for biological feature adaptive learning. According to the method, the relatively mature identity authentication is used to label the feature identity of the biological feature recognition module, the registered feature template is updated adaptively, and the recognition rate is improved, meanwhile, the independent biological feature template and the self-adaptive learning template are respectively used for carrying out biological feature recognition, so the influence of wrong self-adaptive learning on recognition is avoided.

Description

technical field [0001] The invention relates to the field of recognition, in particular to a recognition method and system for self-adaptive learning of biological characteristics. Background technique [0002] Common biometric engine adaptive learning includes: [0003] 1. During the process of user authentication using biometrics collection, the user can manually mark the biometrics collected this time in the system to confirm that the biometrics collected this time are the user's own biometrics, and the system will Automatically add this biometric feature to the user registration feature model for feature comparison, and update the biometric sequence that characterizes the user's features, so as to improve the recognition rate of the biometric feature recognition system. [0004] 2. Through the similarity algorithm. The similarity algorithm can evaluate the similarity between the biometrics collected this time to be identified and the biometrics of the registrant, and u...

AI Technical Summary

Problems solved by technology

[0008] In order to at least solve the problems in the existing technology that completely rely on the active labeling behavior of users, the user experience is poor, and it is difficult to achieve the number of labeling required by the system, the system recognition rate is difficult to improve, and the selection of the similarity threshold is difficult.

Images