Anti-age-interference face recognition method based on multi-space-time information fusion

A face recognition, multi-temporal technology, applied in the field of age-resistant face recognition, can solve problems such as inability to accurately recognize faces

Active Publication Date: 2020-09-01
HANGZHOU DIANZI UNIV
View PDF11 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to provide a face recognition method based on multi-temporal information fusion and anti-age interference. face accuracy

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
  • Anti-age-interference face recognition method based on multi-space-time information fusion
  • Anti-age-interference face recognition method based on multi-space-time information fusion
  • Anti-age-interference face recognition method based on multi-space-time information fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] In order to describe the purpose, technical content and advantages of the present invention more clearly and in detail, further description will be made below in conjunction with specific embodiments of the invention and related drawings. Note that the described embodiments of the present invention are not limited thereto, and the described embodiments are only part of the embodiments of the application, rather than all of them. Based on the implementation content of the present invention, all other implementation modes without creative work by those skilled in the art belong to the protection scope of the present invention. Accordingly, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention but is merely representative of selected embodiments of the invention.

[0069] Existing anti-age interference face recognition technology is mainly divided into...

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 anti-age-interference face recognition method based on multi-space-time information fusion. According to the invention, extracted initial face features are obtained by extracting face features from the time dimension and the space dimension of face images of the same person at different ages in each training sample and then carrying out information fusion, so that the identity features of each person can be expressed fully and the method has certain robustness to age interference. In addition, similarity measurement is further carried out after identity features andage projection features are obtained; and the correlation between the extracted identity features and age features corresponding to each person is gradually reduced through the constraint of a similarity loss function, the smaller the correlation is, the less likely the identity features are affected by age factors, and the higher the accuracy of cross-age face recognition is.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a face recognition method based on multi-temporal information fusion and anti-age interference. Background technique [0002] Today, face recognition technology has been widely used in security, transportation, smart cities and many other fields for identification. As a biometric technology, face recognition technology can effectively extract the key features of the face by combining the knowledge of neuroscience, computer, mathematics and other fields. Accurate recognition of faces. Generally speaking, the face recognition method includes the following four steps: [0003] Step 1: Obtain the face image and its related data. Generally speaking, factors such as the size and quality of the face dataset used for model training will directly affect the performance of the model. Therefore, it is necessary to obtain a large number of face images suitable for model training...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/179G06V40/168G06V40/172G06N3/045G06F18/241
Inventor 颜成钢孟利选殷建孙垚棋张继勇张勇东
Owner HANGZHOU DIANZI 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