Weighted Huber constraint sparse coding-based face recognition method

A sparse coding and face recognition technology, applied in the field of face recognition, can solve problems such as difficulty in distinguishing individuals, and achieve the effects of avoiding inter-class interference, increasing inter-class changes, and expanding effects

Active Publication Date: 2018-09-07
CHONGQING UNIV OF POSTS & TELECOMM
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For faces, the interference of intra-class changes is often greater than the inter-class changes, so it becomes extremely difficult to use inter-class changes to distinguish individuals under the interference of intra-class changes

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
  • Weighted Huber constraint sparse coding-based face recognition method
  • Weighted Huber constraint sparse coding-based face recognition method
  • Weighted Huber constraint sparse coding-based face recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0118] This embodiment provides a face recognition method based on weighted Huber constrained sparse coding, Figure 15 shown, including:

[0119]S101. adopt the regression classifier as the basis of face recognition, introduce L1 regular constraints, and sparse the coding coefficients of the query samples in the training samples to obtain a sparse coding model;

[0120] The general framework based on regression classifiers is explained as follows:

[0121] In general classification problems, training samples are expressed as a dictionary matrix X=[X 1 , X 2 ,...,X c ]∈R m×n ;c is the sample category; is the sample subset of each category of the sample set X; n i is the number of training samples of class i, is the total number of samples. In regression, the training sample X linearly represents the query sample y:

[0122]

[0123] in is the coding coefficient of the query sample y to be determined on the training sample X.

[0124] Regression-based classific...

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 weighted Huber constraint sparse coding-based face recognition method. The method includes the following steps that: with a regression classifier adopted as a basis for face recognition, and L1 regular constraint introduced, sparsification is performed on the coding coefficients of query samples in a training sample set X, so that a sparse coding model is obtained; on thebasis of the sparse coding model, the Huber loss function is used to replace an L1 fidelity term or an L2 fidelity term, so that a sparse robust coding model is obtained; the weight of each pixel point in the training sample set is obtained according to the residuals of the training sample set and the query samples; on the basis of the sparse robust coding model, a weighted Huber constraint sparsecoding model is obtained through using the weights and the threshold of the Huber loss function; the residual vectors of the query samples in the training sample set X are obtained according to the coding coefficients of the query samples; and the recognition rate of the query samples in an occlusion environment is analyzed according to the residual vectors. With the method of the invention adopted, intra-class variation is effectively reduced, inter-class interference can be avoided, the effect of the weight vectors can be enhanced, and a recognition rate can be improved.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a face recognition method based on weighted Huber constrained sparse coding. Background technique [0002] In recent years, face recognition is still a hot research topic. On the one hand, it has great application potential, and on the other hand, it reveals how machine learning can perform feature selection and classification on complete images. Face recognition is considered to be one of the most difficult research topics in the field of biometrics and even in the field of artificial intelligence. On the one hand, this difficulty comes from the characteristics of human biometrics: first, the similarity of human faces. The structure and appearance of faces are similar between different individuals. This similarity is not conducive to the use of human faces to distinguish human individuals; secondly, the variability of human faces. The shape of the human face is very...

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): G06K9/00G06K9/62
CPCG06V40/172G06F18/2136
Inventor 雷大江蒋志杰陈浩张莉萍吴渝
Owner CHONGQING UNIV OF POSTS & TELECOMM
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