Face image feature extraction method and face recognition method based on modular constraint CentreFace

Abstract

The invention discloses a face image feature extraction method and face recognition method based on modular constraint CentreFace, and the method comprises the following steps: obtaining a low-resolution face data set, and carrying out the preprocessing of the data set; selecting a proper basic convolutional neural network according to the task environment of the application; performing joint supervision on the face recognition model on the training data set by using Softmax loss, center loss and mode loss functions to obtain a face recognition model; and extracting a feature representation vector of the face image by using a face recognition model, and judging similarity according to a threshold or giving a face recognition result according to distance sorting. The invention further provides a modular loss function for joint training based on a loss function of a CentreFace algorithm, and a better face recognition model is obtained through a large number of low-resolution face imagesunder monitoring.

Description

technical field [0001] The invention relates to the field of low-resolution face recognition, in particular to a face image feature extraction method and a face recognition method based on modulus constraint CentreFace. Background technique [0002] Face recognition is a biometric technology for identification based on human facial feature information. Face recognition has a wide range of applications in face verification, access control, security monitoring, human-computer interaction and other fields. Currently, face recognition tasks are performed well on convolutional neural networks. Therefore, the convolutional neural network is also the main method to solve the problem of face recognition. Many mature face recognition technologies are aimed at face images in a constrained state. The so-called constrained state means that the environment in which the face is located is relatively ideal without too many complicated interference conditions. Face images in this state ca...

AI Technical Summary

Problems solved by technology

[0005] The main difficulties of low-resolution face detection include: complex and changeable lighting problems, face images in the image sequence may cause shadows or contrast changes due to the illumination angle of the light source or multiple light sources that exist simultaneously in the monitoring environment , which increases the difficulty of face recognition for face detection; the problem of shooting angle and image clarity, if the face imaging distance is far away because of the shooting angle, or the resolution of the image sequence is relatively low, this may also lead to clear face images The accuracy is poor, so that the face cannot be detected correctly; the problem of occlusions, there may be occlusions in the face image, and the face image in the application scene may be affected by the detection results due to occlusions such as glasses and hats. In addition, changes in bangs, beards, etc. may also affect face image detection; complex details of faces change, and face imaging may produce different effects due to changes in expressions. In addition, face images The angle rotation also affects the correct detection rate of face detection in the face recognition process

Images