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

Human face recognition method and apparatus

A face recognition technology, applied in the field of face recognition, can solve the problems of low face recognition rate, no clear maximization of inter-class scatter, and insufficient separability of projection space

Active Publication Date: 2015-05-13
证联网络科技(苏州)有限公司
View PDF3 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The currently proposed small-sample supervised Laplacian Discriminant Analysis (Supervised Laplacian Discriminant Analysis, SLDA) is suitable for small-sample situations, but because the method does not explicitly maximize the inter-class scatter, it leads to separability in the projection space. Not good enough, face recognition rate is not high

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 method and apparatus
  • Human face recognition method and apparatus
  • Human face recognition method and apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0053] See figure 1 A schematic flowchart of an embodiment of a face recognition method of the present invention is shown.

[0054] 101: Obtain a face training data sample and a test data sample, and perform a first dimensionality reduction on the training data sample and the test data sample.

[0055] Among them, when performing dimensionality reduction on the face training data samples, the following processes are included:

[0056] 1) Inp...

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 human face recognition method and apparatus. The method is improved on the basis of existing small sample supervised Laplace discriminant analysis, maximized inter-class scatter is integrated into an objective function of minimized inter-class scatter, Laplace discriminant analysis is used, a projection matrix is obtained by achieving the optimal objective function, and dimensionality reduction is performed on high dimensional human face data. The human face image recognition rate is higher than that of an existing SLDA (Stepwise Linear Discriminant Analysis) method for achieving better human face recognition after dimensionality reduction by means of the human face recognition method.

Description

Technical field [0001] The present invention relates to the field of face recognition, and more specifically to a method and device for face recognition. Background technique [0002] Face recognition has developed into a very popular research topic in computer vision, and it is also the most successful application in the field of image analysis. Face data is often high-dimensional data, and high-dimensional data contains a wealth of information, but in many cases, useful information only needs to be represented by a part of the high-dimensional data. We hope to extract a small number of useful features while reducing data distortion as much as possible. The dimensionality reduction of this kind of data plays a vital role in visualizing the internal structure and pattern classification. In recent years, there have been more and more manifold structures for perceptual observation in computer vision research. For example, principal component analysis is used when the structure is...

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
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/172G06F18/24133
Inventor 张莉罗璇王邦军张召李凡长杨季文
Owner 证联网络科技(苏州)有限公司
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