Face aging method based on a conditional generative adversarial network

A conditional generation and network technology, applied in biological neural network models, neural learning methods, instruments, etc., can solve problems such as low image quality, inconsistent age information, and inability to maintain identity consistency, achieve high resolution, deception, etc. strong effect

Active Publication Date: 2019-03-26
SUN YAT SEN UNIV
View PDF8 Cites 40 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention overcomes the problems of inability to maintain identity consistency in the process of portrait conversion described in the prior art, the generated image does not match the preset age information, and the final image quality is not high.

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 aging method based on a conditional generative adversarial network
  • Face aging method based on a conditional generative adversarial network
  • Face aging method based on a conditional generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] Such as figure 1 The flow chart of a face aging method based on conditional generative confrontation network is shown, including the following steps:

[0037] S1: Collect face data and preprocess the face data;

[0038] S11: Collect public face databases on the network, the condition is that the face database must contain age tags and identity tags, and the main databases include public databases such as FG-NET, CACD and MORPH;

[0039] S12: Perform preprocessing on the obtained image, including face detection, face cropping, and face alignment, etc., and then perform data enhancement on the data, including random cropping, and finally obtain a 224×224 standard face image.

[0040] S13: According to the existing amount of data and the needs of the model, adjust the parameters of the convolutional layer of the model once. According to experience, this method roughly divides the age of people into 16 groups, respectively {0-5,6-10 ,11-15,16-20,21-25,26-30,31-35,36-40,41...

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 provides a face automatic aging mechanism based on a conditional generative adversarial network. A conditional generative adversarial network consisting of four parts is obtained by training a large number of images of different age groups marked with ages, and the conditional generative adversarial network comprises an image generator G, an image discriminator D, an age estimation network AEN and an identity recognition network FRN. Wherein G is trained to generate an aged image, and the aged image is automatically and effectively generated by inputting the young image and a preset age condition. And D, identifying whether the generated old image is a real image or not, and ensuring that the generated old image has deception. Wherein the AEN is used for reducing the difference between the age of the generated image and a preset value, and the FRN is used for ensuring the consistency of portrait identities in the generation process. Through the design of the network structure, end-to-end training of the whole network is achieved, face aging is well shown, and high-quality face aging images with the advantages of identity consistency, high cheating performance, high resolution and the like can be generated.

Description

technical field [0001] The present invention relates to the fields of artificial intelligence and deep learning, and more specifically, relates to a face aging method based on a conditional generation confrontation network. Background technique [0002] Face aging, also known as face age evolution, or aging synthesis, has attracted increasing research interest. In terms of aesthetics, it is defined as rendering a person's face with a natural aging or restoration effect. In face image processing and pattern analysis, face aging is a distinctive task. Its purpose is to generate an old face image with corresponding identity from an input young face image. In recent years, there have been some breakthroughs in the research of face aging, and many related important applications have been produced, such as: face analysis across ages, identity authentication, finding lost children, entertainment, cosmetic surgery, biostatistics or forensic identification Wait. In recent years, w...

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): G06T3/00G06N3/08G06N3/04
CPCG06N3/084G06T3/0012G06N3/045
Inventor 胡海峰黄杨健
Owner SUN YAT SEN UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap