Face image super-resolution reconstruction method based on an attribute description generative adversarial network

Abstract

The invention discloses a face image super-resolution reconstruction method based on an attribute description generative adversarial network, and belongs to the field of digital image / video signal processing. The method is characterized in that a training stage comprises three parts of training sample preparation, network structure design and network training; the network structure design adopts agenerative adversarial network framework and is composed of a generative network and a discriminant network. The generation network comprises a face attribute coding and decoding module and a super-resolution reconstruction module; the discrimination network comprises an attribute classification module, an adversarial module and a perception module; wherein the network training process is carriedout in a mode that a generative adversarial network of a generative adversarial network framework and a discriminant network are alternately subjected to adversarial training; and a reconstruction stage: taking the LR face image and the attribute description information as input, and realizing image coding, attribute adding, image decoding and image reconstruction through a trained generation network. According to the invention, the enhancement of the face information of the low-resolution face image can be completed, and the accuracy of low-resolution face recognition can be improved.

Description

technical field [0001] The invention belongs to the field of digital image / video signal processing, in particular to a face image super-resolution reconstruction method based on an attribute description generation confrontation network. Background technique [0002] Intelligent video surveillance systems have extensive demands on high-quality face images. However, due to complex factors such as low resolution of the acquisition equipment, distance, angle, compression distortion and noise, the faces in the surveillance video often have the characteristics of low resolution and low image quality. Low-quality face images not only seriously affect people's subjective visual experience, but also seriously affect a series of intelligent operations such as face recognition. Therefore, how to improve the quality of face images under surveillance video is a key problem to be solved urgently. [0003] When the existing super-resolution reconstruction technology is used to improve th...

AI Technical Summary

Problems solved by technology

Therefore, face images produced by generative models can easily produce faces that do not actually exist

The purpose of these methods is mainly to generate face images with good visual experience, but for extremely low-resolution face images, it is difficult to reconstruct the real attribute information that represents the identity of the face

Images