Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Face age estimation method based on gan extended multi-ethnic feature collaborative selection

A technology of race and face database, which is applied in the field of face age estimation, can solve the problems of restricting the age recognition of yellow, brown and other race pictures, so as to improve the recognition accuracy, improve the accuracy, and improve the convenience and accuracy Effect

Active Publication Date: 2021-12-14
NANJING UNIV OF INFORMATION SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the research is based on existing data sets. Because there are too few samples of yellow, brown and other races in many existing large-scale foreign data sets, the age recognition of yellow, brown and other race pictures is greatly limited.

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 age estimation method based on gan extended multi-ethnic feature collaborative selection
  • Face age estimation method based on gan extended multi-ethnic feature collaborative selection
  • Face age estimation method based on gan extended multi-ethnic feature collaborative selection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] DRAWINGS Examples and further detailed description of the present invention, the following Examples are intended to explain the present invention and the present invention is not limited to the following embodiments.

[0035] Generated against the network (GAN) generated by a model consisting of G and D discriminant model, by way of learning against the number of training set and a new data sample. 2014 Goodfellow published "Generative Adversarial Networks" article, the formula against the network debut in academia, the main idea from game theory (that is, the interests of the two is zero, resulting in one of the official party to the loss). Since then, GAN is applied to solve practical problems, such as the study of language problems, speech processing, chess competition procedures. Generating model captures G data distribution of the sample, with a subject distribution (uniform, Gaussian, etc.) to generate a noise sample z a real similar training data, the effect is more ...

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 present invention discloses a face age estimation method based on GAN extended multi-ethnic feature cooperative selection. Firstly, the multi-style face samples are simulated and generated through the generative confrontation network, so as to quickly and large-scale expand the faces of different races. Face database, so as to improve the accuracy of age information recognition of yellow, brown and other races. Then use the convolutional neural network to pre-train the original data set, and then perform further fine training based on the expanded face age database. Finally, the Sub-CNN of the four races is combined with the joint feature selection based on the group sparse algorithm to solve the age estimation problem based on the face image. The present invention obtains a human face age estimation model with more generalization ability, and can also greatly improve the performance of many age human face recognition systems, making up for the inadequacies of previous studies.

Description

technical field [0001] The invention relates to a method for estimating the age of a human face, in particular to a method for estimating the age of a human face based on collaborative selection of multi-ethnic characteristics based on GAN expansion. Background technique [0002] With the rapid development of related theories and applications of human-computer interaction, age information, as an important biological characteristic of human beings, has many application requirements in this field and has an important impact on the performance of face recognition systems. However, most of the research is based on existing data sets. Because there are too few samples of yellow, brown and other races in many existing large data sets abroad, the age recognition of yellow, brown and other race pictures is greatly limited. Contents of the invention [0003] The technical problem to be solved by the present invention is to provide a face age estimation method based on GAN extended ...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/16G06V40/168G06V40/178G06F18/214
Inventor 田青沈传奇毛军翔孙元康秦璇黄媛沅
Owner NANJING UNIV OF INFORMATION SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com