Identity recognition method and electronic equipment

Abstract

The embodiment of the invention relates to an identity recognition method and electronic equipment, and the method comprises the steps: obtaining a to-be-recognized image which comprises a face imageof at least one to-be-recognized person, and obtaining the face image of the to-be-recognized person based on the to-be-recognized image; acquiring face features of the to-be-recognized person based on the face image; obtaining a first weight coefficient of the face features; obtaining auxiliary features of the to-be-identified person; obtaining a second weight coefficient of the auxiliary features; according to the first weight coefficient and the second weight coefficient, combining face features and the auxiliary features to obtain recognition features of the to-be-recognized person; and matching the identification features of the to-be-recognized person with the identification features of the known identity to obtain the identity of the to-be-recognized person. The identification features are obtained by combining the face features and the auxiliary features of the to-be-identified person and the respective weight coefficients, the identity of the to-be-identified person can be comprehensively judged by combining multiple features, and the influence of poor face image quality on the identity identification effect is reduced, so that the accuracy of identity identification is improved.

Description

technical field [0001] The embodiment of the present invention relates to the technical field of identification, in particular to an identification method and electronic equipment. Background technique [0002] Identification technology is more and more used in human production and life. Among the current identification technologies, face recognition technology that uses people's facial features for identification is widely used. Current face recognition usually uses neural network models based on machine learning for recognition. That is to train a neural network model based on machine learning, and then use the recognition model to extract face features from face images of known identities to obtain face features of known identities. When identifying face images with unknown identities, first use the recognition model to extract face features to obtain face features of unknown identities, and then match face features of unknown identities to face features of known identit...

AI Technical Summary

Problems solved by technology

Therefore, when performing face recognition, it is also required that the face is not occluded and the illumination is uniform and stable, and the recognition effect is poor for faces with poor lighting conditions or occlusions.

Images