Super-division model training and face recognition method and device, medium and electronic equipment

Abstract

The invention relates to the field of face recognition, in particular to a super-division model training and face recognition method and device, a computer readable storage medium and electronic equipment, and the method comprises the steps of obtaining a first high-quality face image sample and a corresponding low-quality face image sample, performing super-resolution reconstruction processing on the low-quality face image sample by the to-be-trained model to generate a corresponding target high-quality face image, and obtaining a first loss function of the to-be-trained model; obtaining identity information, obtaining a second high-quality face image sample corresponding to the identity information, and constructing an image multi-component system; extracting a plurality of face features of a plurality of face images in the face image multi-tuple and calculating a second loss function of the to-be-trained model; and iteratively updating neural network parameters of the to-be-trained model through the first loss function and the second loss function so as to train the super-division model. Through the technical scheme of the embodiment of the invention, the problem of relatively low recognition efficiency of a low-quality face image can be solved.

Description

technical field [0001] The present disclosure relates to the technical field of face recognition, and in particular, to a super-resolution model training method, a face recognition method, a super-resolution model training device, a face recognition device, a computer-readable storage medium, and electronic equipment. Background technique [0002] Face recognition is a biometric technology for identification based on human facial feature information. With the development of software and hardware, deep learning has been more and more widely used in the field of face recognition. Face recognition can detect and track faces in images according to computers, quickly identify specific people, and make respond accordingly. [0003] In the prior art, a video camera or camera is usually used to collect images or video streams containing human faces, and to track the images, and then perform facial recognition on detected human faces. [0004] However, in some application scenarios...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present disclosure is to provide a super-resolution model training method, a super-resolution model training device, a computer-readable storage medium, and electronic equipment, which can solve the problem of poor recognition efficiency of low-quality face images

Images