Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Face image restoration method based on multi-discriminator generative adversarial network

A face image and repair method technology, applied in the biological neural network model, image enhancement, image data processing, etc., can solve the problem that it is difficult to provide face repair images stably, achieve direct use and promotion, and reduce the amount of parameters and the computational effect

Active Publication Date: 2019-05-21
SOUTH CHINA UNIV OF TECH
View PDF6 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the generative confrontation network can repair some face images, it is difficult for existing technologies to provide a more realistic and realistic face repair image stably.

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 restoration method based on multi-discriminator generative adversarial network
  • Face image restoration method based on multi-discriminator generative adversarial network
  • Face image restoration method based on multi-discriminator generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be further described in detail below in conjunction with the embodiments and the accompanying drawings, but the embodiments of the present invention are not limited thereto.

[0048] Such as Figure 1-5 , a face image repair method based on multi-discriminator generation confrontation network, including the following steps

[0049] Step (A): preprocessing the images in the public face image database, and inputting them into the generator to obtain generated images;

[0050] Step (B): The real image and the generated image are input to multiple discriminators to obtain feedback values;

[0051] Step (C): The feedback values ​​of multiple discriminators are used as the confrontation loss, and the generator and the discriminator in the generative confrontation network are trained against each other by combining the perceptual loss and the reconstruction loss;

[0052] Step D: Input the missing face image into the trained generator to obtain the...

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 restoration method based on a multi-discriminator generative adversarial network, and the method comprises the following steps: (1) carrying out the preprocessingof images in a disclosed face image database, and inputting the images into a generator, so as to obtain a generated image; (2) inputting the real image and the generated image into a plurality of discriminators to obtain a feedback value; (3) taking the feedback values of the plurality of discriminators as confrontation loss, and performing confrontation training on the generative adversarial network by combining the perception loss and the reconstruction loss; and (4) inputting the missing face image into the trained generator to obtain a repaired face image. Aiming at the problem of repairing the shielded or damaged face image, a generative adversarial network structure with multiple discriminators is adopted, so that the problem of low authenticity of the repaired image is solved, andthe repaired image is more natural and more real.

Description

technical field [0001] The invention relates to the fields of computer vision and pattern recognition, in particular to a face image restoration method based on a multi-discriminator generation confrontation network. Background technique [0002] With the development of science and technology, electronic devices such as mobile phones, tablet computers and digital cameras have been widely popularized. Using electronic devices to take pictures has become a common behavior in people's daily life. At the same time, with the development of the mobile Internet, people are keen on entertainment and sharing social activities related to face photos, and the aesthetic requirements for face images obtained by taking photos are getting higher and higher. Existing electronic devices provide a series of camera functions, which can automatically beautify face images, including functions such as whitening, acne removal, and automatic makeup, but lack related functions for face image restor...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/00G06N3/02
Inventor 林少文丁长兴
Owner SOUTH CHINA 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
Eureka Blog
Learn More
PatSnap group products