Multi-view face recognition method based on fractional order sparse representation

A sparse representation and face recognition technology, applied in the field of classification and recognition, can solve the problems of affecting recognition speed and effect, unclear face image, and increased calculation cost, so as to improve the ability and stability of face recognition and improve the user experience. Experience and reduce the effect of detail changes

Pending Publication Date: 2020-06-09
YANGZHOU UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The traditional face recognition method based on sparse representation will increase the calculation cost as the face sample dimension increases. Sometimes the face image is not clear or occluded, which will affect the recognition speed and effect

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
  • Multi-view face recognition method based on fractional order sparse representation
  • Multi-view face recognition method based on fractional order sparse representation
  • Multi-view face recognition method based on fractional order sparse representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] like figure 1 Shown is a multi-view face recognition method based on fractional sparse representation, comprising the following steps:

[0035] Step 1: Input the multi-view face image set A and the multi-view test image set Y, the multi-view face image set A is a training dictionary that contains the multi-view images of each face, defined as: where A i is all images of the i-th type of face, and the Y is a group of multi-view test face images containing M perspectives.

[0036] Step 2: Perform singular value decomposition on A, A=PΛQ T , Λ=diag(λ 1 ,λ 2 ,...,λ r ), where r is the rank of A, P=(p 1 ,p 2 ,...,p r ) and Q=(q 1 ,q 2 ,...,q r ) are the left and right singular value matrices of A, respectively.

[0037] Step 3: For a given non-negative fractional order parameter α, calculate the corresponding fractional order training dictionary matrix A α , assuming α is a fraction and satisfies 0≤α≤1, the matrix A α is the fractional order training dictionar...

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 a multi-view face recognition method based on fractional order sparse representation. The method comprises the following steps: 1, inputting a multi-view face image set A and amulti-view test image set Y; 2, singular value decomposition is performed on A; 3, for a given non-negative fractional order parameter alpha, calculating a corresponding fractional order training dictionary matrix A alpha; 4, solving a joint sparse representation coefficient matrix X by using the new fractional order training dictionary; 5, classifying the multi-view test image set Y by using a Classi (Y) formula; and 6, outputting the face category of the Y; according to the invention, face recognition based on sparse representation is used as a basis; fractional order embedding, the main idea of the method is that a training dictionary matrix of a human face is constructed through fractional order embedding; the dictionary is introduced into a sparse representation classification framework by using an optimization method, so that the extracted face features not only reduce detail changes of the face, but also eliminate noise data caused by shielding, the face recognition capabilityand stability are improved, and the user experience is further improved.

Description

technical field [0001] The invention relates to the field of classification recognition in machine learning, in particular to a multi-view face recognition method based on fractional sparse representation. Background technique [0002] With the rapid development of modern information technology, the technology for identity authentication has transferred to the biometric level. Modern biometric technology is mainly through the close combination of computer and high-tech means, using the inherent physiological characteristics and behavioral characteristics of the human body to identify personal identity. Face recognition is a technology based on human facial feature information. Use a camera or camera to collect images or video streams containing faces, and automatically detect and track faces in the images, and then use the existing face database to determine one or more people in the scene. At present, the research scope of face recognition mainly includes several aspects:...

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): G06K9/00G06K9/46G06K9/62
CPCG06V40/172G06V40/168G06V10/513G06V10/462G06F18/2136
Inventor 袁运浩张超李云强继朋
Owner YANGZHOU 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