Multi-dimensional output face quality assessment method and electronic equipment based on deep learning

Abstract

The invention discloses a method for evaluating the quality of human faces based on deep learning multi-dimensional output: prepare training data sets, Score training sets, Class training sets, Mask training sets, Pose training sets; train network models, randomly select from four training sets Select a part of the pictures and merge them into a batch of pictures, send them to the neural network model, and get the output values ​​of the four branches after forward reasoning through the neural network, and calculate the loss value of the corresponding branch according to which data set the input picture comes from. Finally, add the loss value of each branch according to different weights to obtain the total loss value, which is used for network backpropagation to update network parameters; predict the face image to be tested, input a face image, and send it after preprocessing Enter the trained neural network model for forward reasoning, output the predicted values ​​of the four branches, and finally add the output values ​​of the four branches according to the weight to obtain the final comprehensive evaluation score of face quality. The invention also provides corresponding electronic equipment.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and more particularly, relates to a multi-dimensional output face quality assessment method and electronic device based on deep learning. Background technique [0002] During the face capture process of edge devices, due to the influence of environmental changes and human motion, there are low-quality face images such as blur, occlusion, and posture changes in the captured face images. These low-quality human images will be greatly reduced. Accuracy of face recognition systems. At the same time, the storage space and transmission bandwidth of edge devices are very limited, and a large number of low-quality face pictures are not conducive to the storage and transmission of face pictures. In order to be able to select one or more high-quality face images from a large number of face images, a face quality assessment method is needed. [0003] The factors that affect the quality of the fa...

AI Technical Summary

Problems solved by technology

[0004] In view of the above defects or improvement needs of the prior art, the present invention provides a face quality assessment method based on multi-dimensional output of deep learning, which is used to solve the problem of increasing time-consuming and computing resources when multiple models run at the same time, increasing human Accuracy of face quality assessment

Images