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

A super-resolution reconstruction and face image technology, which is applied in the field of digital image/video signal processing, can solve problems such as the difficulty in reconstructing the real attribute information of face identity, and achieve the effects of improving learning ability, promoting generation ability, and enhancing quality

Pending Publication Date: 2019-04-12
BEIJING UNIV OF TECH
View PDF5 Cites 66 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Face image super-resolution reconstruction method based on an attribute description generative adversarial network
  • Face image super-resolution reconstruction method based on an attribute description generative adversarial network
  • Face image super-resolution reconstruction method based on an attribute description generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0052] The following describes the implementation examples of the present invention in detail with reference to the accompanying drawings of the specification:

[0053] A face image super-resolution reconstruction method based on attribute description generation confrontation network, divided into training phase and reconstruction phase, the overall flow chart is attached figure 1 As shown; the overall structure diagram of the network for generating the confrontation network is attached figure 2 Shown.

[0054] (1) In the process of preprocessing the training data, in order to reduce errors caused by the background and posture of the face image, the present invention obtains the training sample library through three stages. In the first stage, considering that the common face data sets "CelebA" and "LFW" at home and abroad are obtained from actual monitoring, and their universality and important experimental comparison significance, the present invention uses data including 202,599...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06T3/40G06K9/00G06N3/04G06N3/08G06T11/00
CPCG06N3/08G06T3/4053G06T11/00G06V40/161G06V40/168G06N3/045Y02T10/40
Inventor 李晓光董宁李嘉锋张辉卓力
Owner BEIJING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products