Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Face recognition method and device

A face recognition and face testing technology, applied in the field of face recognition, can solve the problems of not satisfying rotation invariance, long calculation time, poor recognition rate, etc., to reduce redundancy, improve recognition performance, and reduce complexity Effect

Active Publication Date: 2012-10-24
TCL CORPORATION
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the embodiments of the present invention is to provide a method and device for face recognition, which aims to solve the problems that the output of the existing face recognition technology system does not satisfy the rotation invariance, the calculation time is long and the recognition rate is poor

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
  • Face recognition method and device
  • Face recognition method and device
  • Face recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] Such as figure 1 The flow chart of the face recognition method provided by the present invention is shown, and for the convenience of description, only the parts related to the embodiment of the present invention are shown.

[0023] In step S101, the test image is generated into a plurality of test sub-images through circular symmetric Gabor transformation.

[0024] In the embodiment of the present invention, the test image is subjected to circular symmetric Gabor transformation to generate a plurality of corresponding test sub-images. For example, the test image can correspondingly generate 5, 6, or 7 test sub-images. Preferably, it is better to generate five test sub-images after the test image is subjected to circular symmetric Gabor transform.

[0025] In the embodiment of the present invention, since the ring-symmetric Gabor transform is invariant to rotation, the problem of discretization of directions in the traditional Gabor wavelet transform is avoided. Moreo...

Embodiment 2

[0039] Such as figure 2 Shown is the flow chart of the method for subjecting the sample images in the sample library to the circular symmetric Gabor transform and calculating the corresponding sample face feature space through PCA provided by the present invention. The method provided in the second embodiment can be compared with that in the first embodiment The method is used in combination, but not limited to the method provided in this example. For ease of description, only parts related to the embodiments of the present invention are shown.

[0040] In step S201, N sample images are subjected to Circular Symmetrical Gabor Transformation (CSGT) to generate multiple sample sub-images.

[0041] In the embodiment of the present invention, there may be N sample images in the sample image library, and N is a positive integer. Each sample image is subjected to circular symmetric Gabor transformation to generate multiple corresponding sample sub-images, and the test image is sub...

Embodiment 3

[0060] Such as image 3 Shown is the method flowchart of step S203 in the second embodiment of the present invention, which is a refinement of step S203 in the first embodiment, therefore, the method provided in the third embodiment can be combined with the methods in the first and second embodiments Use, but not limited to the method provided in this example. For ease of description, only parts related to the embodiments of the present invention are shown.

[0061] In step S301, the covariance matrix of each sample sub-image matrix is ​​calculated, and the eigenvalues ​​and eigenvectors corresponding to each covariance matrix are obtained.

[0062] In step S302, according to the size of the eigenvalues ​​corresponding to each covariance matrix, several eigenvectors corresponding to each covariance matrix with larger eigenvalues ​​are respectively selected to form a corresponding sample eigenface space.

[0063] In the embodiment of the present invention, the eigenvalues ​​c...

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 is applicable to the field of image processing, and provides face recognition method and device. The method comprises the steps: generating a plurality of test subimages from a test image by circularly symmetrical gabor transformation; blocking each test subimage to obtain a corresponding test subimage matrix, and respectively projecting each test subimage to a corresponding sample feature face space to obtain a corresponding test face feature space; respectively calculating Euclid distances of the test face feature spaces and those of the sample face feature spaces to recognize the similarity of a sample image and the test image. The circularly symmetrical gabor transformation has rotation without deformation, thus avoiding the direction discretion problem caused by adopting traditional gabor wavelet transformation, and obviously reducing redundancy. In addition, the high-dimensional test image is projected to the low-dimensional sample feature face space for recognition, thus greatly reducing the calculation complexity and improving the recognition property.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a face recognition method and device. Background technique [0002] With the advancement of science and technology, face recognition has been widely used as a typical biometric technology in security, surveillance, video applications and other fields. Existing face recognition technology generally adopts traditional Gabor wavelet transform (Gabor) and principal component analysis (Principal Component Analysis, PCA) technology for recognition. However, the selection of the direction of the traditional Gabor transform is discrete, which leads to the output of the system not satisfying the rotation invariance, and the feature dimension extracted by the traditional Gabor transform is more, which makes the feature information of the face redundant, which is not conducive to the main function of the face. Feature expression, extraction, recognition. In addition, when traditional PCA i...

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): G06K9/00G06K9/46
Inventor 王甜甜邵诗强
Owner TCL CORPORATION
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com