Age-tolerant face recognition method

A face recognition and age person technology, applied in the field of face recognition that tolerates age changes, can solve problems such as face recognition interference, achieve safety and reliability, expand training data sets, and reduce difficulty

Inactive Publication Date: 2018-11-20
JIANGSU UNIV
View PDF0 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, under the influence of various factors such as different lighting and age, the face will cause greater or lesser interference to face recognition.

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
  • Age-tolerant face recognition method
  • Age-tolerant face recognition method
  • Age-tolerant face recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be further described below in conjunction with accompanying drawing.

[0028] Such as figure 1 Shown, method of the present invention comprises as follows:

[0029] First of all, according to the existing face pictures, with the help of generative confrontation network to generate different ages (respectively 0-10 years old, 11-20 years old, 21-30 years old, 31-40 years old, 41-50 years old, 51-60 years old) , 61-70 years old, 71-80 years old, 80-90 years old, and over 90 years old) face, expand the number of pictures in the cross-age face database, and reduce the difficulty of collecting pictures of the same person in different periods. Using the constructed cross-age face database, select the faces under some age groups as the training data set, and select the faces under the remaining age groups as the test data set. Then train the neural network VGG-face model, through the forward calculation of the error back propagation algorithm, 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 an age-tolerant face recognition method. The depth network VGG-Face is trained to perform age-tolerant face recognition, and it is necessary to collect face data of different age stages for training, but collecting faces from the same person at different times is a difficult task, thus the invention completes the generation of human faces at different ages by means of the generation antagonism network, and a cross-age database composed of face pictures of a plurality of persons at different ages is constructed. Then, the faces at part of the different ages in the database form a training set, and the faces on the rest different ages form a testing set, and the network is trained by the two sets, the classification of different faces is achieved through softmax, so as to complete the age-tolerant face recognition. A main use of the invention is to realize cross-age face recognition under the condition of incomplete pictures of people at different times.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a face recognition method that tolerates age changes. Background technique [0002] Nowadays, with the rapid development of science and technology, biometric identification technology can be said to be developing particularly rapidly. Among them, face recognition technology is known as one of the most difficult research topics in the field of biometric recognition, and it is also a very popular research topic. [0003] As early as the last century, Galton published two articles on the use of faces for identification in the "Nature" magazine, which mainly analyzed the face recognition ability of human beings. The earliest research paper on automatic face recognition was a technical report published by Chan and Bledsoe at Panoramic Research Inc. in the 1970s, and it has a history of several decades. [0004] In recent years, research on automatic face recognition has mad...

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): G06K9/00G06F17/30G06N3/08
CPCG06N3/08G06N3/084G06V40/178G06V40/16G06V40/172
Inventor 毛启容盛梦娇陆海棠张飞飞许国朋
Owner JIANGSU 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