A method and system for face authentication

Abstract

The invention discloses a face authentication method, which comprises the following steps: collecting multi-frame images containing a same unauthenticated face target to obtain sample features of each frame image containing the same unauthenticated face target; utilizing a sorter judgment model obtained after the training according to a feature database, so as to carry out the authentication of the sample features of each frame image containing the same unauthenticated face target; updating the feature database at least once in previous authentication processes; syncretizing the authentication result of the sample features of the multi-frame images containing the same unauthenticated face target to obtain the authentication result of the target; adding all the sample features of the unauthenticated face target with a confidence level of the syncretized authentication result higher than a preset confidence threshold into the feature database, so as to realize the update of the feature database. The invention also discloses a face authentication system. The face authentication method and the system of the invention can realize automatic updating of the authentication target samples, so as to improve the anti-interference ability of the face authentication system.

Description

technical field [0001] The invention relates to pattern recognition technology, in particular to a face authentication method and system. Background technique [0002] With the rapid development of current computer technology, computer processing capabilities have been greatly improved; at the same time, related technologies in the fields of pattern recognition and computer vision have also achieved rapid development. Face authentication is a hot spot in research and application in related fields. , has important practical value and has been widely used in many fields such as security, entertainment, and human-computer interaction. [0003] Face authentication refers to the use of face detection, facial feature point positioning and other technologies to obtain the face position information in the image, based on the face position information to extract the information contained in the face image through a certain algorithm, and according to A method of judging whether the ...

AI Technical Summary

Problems solved by technology

[0018] Since the classifier judgment model that ultimately determines the face authentication effect is obtained by training the training samples, the offline training process in the prior art is closed. That is, after the training sample is selected during the training of the classifier, it cannot be conveniently updated according to the actual application scenario in the subsequent face authentication process

Therefore, when the use scene of the face authentication system changes or the facial features of the authentication target itself change, the recognition effect will deteriorate rapidly, which seriously affects the effect of face authentication.

Images