Identity recognition method and system

Abstract

The embodiment of the invention provides an identity recognition method and system. The method comprises the steps of obtaining a face image and an iris image of a to-be-recognized user; obtaining a face attribute feature vector, a face feature vector template, an iris attribute feature vector and an iris feature vector template; calculating the similarity between the face feature vector template and the sample face feature vector template to obtain a face comparison result; calculating the similarity between the iris feature vector template and the sample iris feature vector template to obtain an iris comparison result; carrying out fusion calculation to obtain a comparison score corresponding to the to-be-identified user and the personnel number; and if the comparison score is greater than the set score threshold, determining that the identity of the to-be-identified user is the identity corresponding to the personnel number. According to the embodiment of the invention, on one hand, a mature and complete single biological feature recognition method is fully used, and on the other hand, the attribute features of the face and the iris and the correlation between face recognition and iris recognition are fully considered, so that the recognition accuracy is effectively improved.

Description

technical field [0001] The present invention relates to the technical field of identification, and more specifically, to an identification method and system. Background technique [0002] In recent years, with the rapid development of computer technology and the improvement of people's requirements for the accuracy and reliability of social security and identity identification, biometric technology based on human body feature image processing, such as fingerprint, face, iris recognition, etc., It has been more and more widely used in identity comparison and verification in scenarios such as mobile phones, access control, monitoring, security, and human-computer interaction, and has shown better applicability than traditional methods. However, due to the defects of biometrics itself and the susceptibility to interference from the external environment during the collection process, there are still certain problems in the practical application of single-mode biometrics recognit...

AI Technical Summary

Problems solved by technology

[0004] However, the current multi-biological feature fusion method is mainly to fuse at the feature level, that is, to merge the feature vectors of different modes into a whole feature vector and then compare and identify it, thus giving up the mature and perfect single biological features. Feature recognition method; or fusion at the decision-making level, that is, through a single AND or logic recognition method (both pass for recognition or one pass for recognition), but do not fully consider the attribute characteristics of the face and iris and the face Relevance of recognition and iris recognition

Images