A cross-aging face recognition method based on unified generation model

A face recognition and model generation technology, applied in the fields of computer vision and machine learning, can solve problems such as large computing resources, cumbersome computing process, and unreal face pictures

Active Publication Date: 2019-01-22
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF9 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the generation methods all have strong assumptions (assuming that the samples satisfy a multi-dimensional normal distribution), sometimes the generated face pictures will not be real, and the calculation process is too cumbersome and requires a lot of computing resources.

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
  • A cross-aging face recognition method based on unified generation model
  • A cross-aging face recognition method based on unified generation model
  • A cross-aging face recognition method based on unified generation model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0076] According to the method of the present invention, first collect a certain number of face pictures and record the ID numbers and ages of the people corresponding to these pictures, according to the patent of the present invention, use the Python language to write a face alignment program, and align all the collected pictures Processing, then divided into training pictures and dictionary library pictures; then write the cross-aging face recognition program based on the depth model and the age picture generation program based on the conditional generation model, and use the training pictures to train the parameters of the two corresponding models of the present invention: recognition model and generative model; then use the generative model to generate face pictures of all age groups from the dictionary pictures; then extract features from the generated pictures through the face recognition model and perform average processing to establish a dictionary; when applying, the ne...

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 cross-aging face recognition method based on a unified generation model, which belongs to the technical field of computer vision and machine learning, and relates to the cross-aging recognition problem in face recognition. The method first assumes that the facial identity feature extracted from depth network can not completely eliminate the aging information on human face,and then the missing age pictures in the dictionary library are filled in by using the generation method, then the feature of each picture is extracted by face recognition network, and then the relevant image features are fused, and then the cosine similarity between the feature of each picture to be tested and each feature in the dictionary library is obtained. Finally, the object with the largest cosine similarity is taken as the correct matching object. The method of the invention can be used for cross-aging face recognition under various scenes.

Description

technical field [0001] The invention belongs to the technical field of computer vision and machine learning, and relates to the problem of cross-aging recognition in face recognition. Background technique [0002] Face recognition is a biometric technology for identification based on human facial feature information. It is a hot issue in the field of computer vision and machine learning in recent years, and has a wide range of applications in human-computer interaction, safe driving, and attention analysis. And because the age span of people is sometimes very large, this will cause the facial aging characteristics of people to be particularly obvious, and cross-aging face recognition is aimed at exactly this kind of problem. Cross-aging face recognition can help people find lost children, age prediction, etc. In recent years, the problem of cross-aging face recognition has been further developed based on the development of metric learning and deep learning. Existing cross...

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): G06K9/00
CPCG06V40/178G06V40/172G06V40/168
Inventor 陈家祥柏邱建潘力立
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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