Method and device for face recognition and computer device

Abstract

The invention discloses a method and device for face recognition and a computer device. In the method provided by the invention, feature vectors of any two samples in a preset training set are extracted according to a preset face feature extraction model, normalization processing is performed, a fusion feature vector and reference similarity of the any two samples are obtained, all the mutually different two samples are traversed in sequence, fusion feature vectors and reference similarity of all the mutually different two samples in the preset training set are obtained, a regression model istrained according to the fusion feature vectors and reference similarity of all the mutually different two samples, and the trained regression model is utilized to recognize a face picture to be recognized. According to the method provided by the invention, the regression model is trained according to all the fusion feature vectors and reference similarity in the preset training set, the trained regression model can effectively distinguish samples with different categories of marks, and in recognition of the face picture to be recognized, an effect and the accuracy rate of face recognition canbe effectively improved.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a face recognition method, device and computer device. Background technique [0002] Face recognition is a biometric technology for identification based on human facial feature information. It is widely used in fields such as identity verification, security monitoring, access control and attendance systems, and judicial criminal investigation. Face recognition mainly includes processes such as face detection, face alignment, face feature extraction, and determination of face similarity. Among them, the determination of face similarity is an important link in face recognition, which can directly affect the result of face recognition. At present, the existing methods for determining the similarity of human faces mainly include: (1) methods for determining the similarity of human faces based on distance, such as Euclidean distance, cosine distance or Mahalanobis distance...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a face recognition method, device and computer device, aiming to solve the problems of poor effect and low efficiency in existing face recognition methods

Images