Human face recognition system and method based on second-order two-dimension principal component analysis

A face recognition system and principal component analysis technology, applied in the field of face recognition, can solve the problems of low recognition accuracy, long running time of image vector space features, etc.

Inactive Publication Date: 2011-02-09
CHONGQING UNIV OF POSTS & TELECOMM
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to propose a new type of second-order two-dimensional two-dimensional Eigenface (2D) 2 PCA face recognition method, referred to as the second-order principal component analysis method sec-(2D) 2 PCA

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
  • Human face recognition system and method based on second-order two-dimension principal component analysis
  • Human face recognition system and method based on second-order two-dimension principal component analysis
  • Human face recognition system and method based on second-order two-dimension principal component analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The implementation of the technical solution of the present invention will be further described below with reference to the drawings and specific embodiments. Such as figure 1 Shown is that the present invention adopts Sec-(2D) 2 Flowchart of the PCA method to determine the feature matrix.

[0028] The acquisition module collects face image information to obtain any image matrix A with a size of m×n, and constructs the original image matrix A i (i=1, 2, Λ, M), obtain original image collection I={A 1 , A 2 ,Λ,A M}. Control processor issues control commands to use on raw image set I (2D) 2 PCA (two-way two-dimensional PCA) method, learning the optimal projection matrix X reflecting row feature information 1 (size n×r 1 ) and the optimal projection matrix Z reflecting column feature information 1 (the size is m×c 1 ), to extract the feature vector reflecting the illumination information.

[0029] According to the above optimal projection matrix, the control proc...

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 requests to protect a face recognition system and a face recognition method which are based on the second-order two-dimensional principal component analysis, and belongs to the fields of image processing technology, computer vision technology and mode identification technology. The invention provides the face recognition method which has low computational complexity and is based on the second-order two-dimensional principal component analysis. The method researches the face recognition problem in the condition of illumination change, and provides the face recognition method of the second-order two-dimensional principal component analysis. The face recognition method comprises: respectively applying the (2D)<2>PCA technology to an original image matrix set and a residual image matrix set to obtain a first-order feature matrix and a second-order feature matrix, thereby determining reconstructed images of sample images and reconstructed images of residual images; superimposing the two reconstructed images to obtain reconstructed images of original images. The method of the invention has higher recognition accuracy, and save more computing time than the eigenface method and the second-order eigenface method. The method of the invention can be widely used in the image recognition field.

Description

Technical field: [0001] The invention relates to the technical fields of image processing, computer vision and pattern recognition, in particular to a face recognition method. Background technique: [0002] In recent years, face recognition is a hot topic in the field of computer vision and pattern recognition. The literature P.N.Belhumeur, J.P.Hespanha, D.J.Kriegman.Eigenfaces vs.fisherfaces: class-specific linear projection.IEEE Trans.Pattern Anal.Mach.Intell, 1997,19,7:711-720 proposes an eigenface method (also known as PCA method), which is an effective feature extraction and dimensionality reduction method, is widely used in face recognition. However, since real faces are very complex, such as face images with large illumination changes, a single eigenface set cannot effectively describe face images. In order to overcome this, Wang and Tan proposed a second-order eigenface method (referred to as Sec-PCA method), that is, the PCA method is used in the original image v...

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 Patents(China)
IPC IPC(8): G06K9/00
Inventor 王汝言罗仁泽冉瑞生
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