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

A New Method of Face Feature Description

A face feature and feature description technology, applied in the field of face recognition, can solve the problem of not considering the differences of different face areas, and achieve the effect of accelerating computing efficiency

Active Publication Date: 2017-11-17
XIAMEN UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most local feature descriptors do not consider the differences between different face regions, as well as the global information that is beneficial to face recognition

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
  • A New Method of Face Feature Description
  • A New Method of Face Feature Description
  • A New Method of Face Feature Description

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] Below in conjunction with accompanying drawing and embodiment the method of the present invention is described in detail, present embodiment is carried out under the premise of technical scheme of the present invention, has provided embodiment and specific operation process, but protection scope of the present invention is not limited to following the embodiment.

[0043] see figure 1 , the implementation of the embodiment of the present invention includes the following steps:

[0044] S1. Prepare face image training sample set (a i(1) ,a i(2) ,...,a i(pi) ), i=1,2,...,C, C is the number of face training sample categories (number of targets), C is a natural number, p i is the total number of training samples contained in class i, a i(1) Indicates the training sample of the first face image in the i-th target. Specifically include: the total training sample set size in the present invention is:

[0045] (a 1(1) ,a 1(2) ,...,a 1(p1) ,a 2(1) ,a 2(2) ,...,a 2(p...

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

A new face feature description method involves face recognition. First, use the training set to create a difference image set for each image, and then extract the LTPBP feature description vector from each image in the difference image set according to the prior regulations, and then combine the LTPBP feature description vectors into 10 different feature matrices according to the agreed rules 1. Use the LDA method to learn the generated feature vector matrix once to obtain 10 projection matrices, and then use the projection matrix to perform projection learning on the original LTPBP feature description vector to obtain the dimensionality-reduced LTPBP feature description vector. The low-dimensional LTPBP feature description vectors obtained in the image are concatenated to generate the PPC feature description vector. The LTPBP texture feature description vector combined with the drift difference method is proposed, which accelerates the operation efficiency of feature extraction.

Description

technical field [0001] The present invention relates to face recognition, in particular to a new face feature description method micro-pattern coding PPC (Primitive Pattern Coding). Background technique [0002] How to make computers understand the world like human eyes, and assist humans to do something meaningful, the discipline of computer vision was born. Computer vision originally originated from the field of digital image processing. It was separated from the 1960s and became an independent subject research. It has been widely used in aerospace, automatic navigation, industrial inspection, medical research and clinical diagnosis and treatment, security monitoring and tracking, National defense, transportation, remote sensing and many other important fields. [0003] With the rapid development of today's society, there are various identity authentications in all aspects of people's life. In some security fields, it is already difficult to ensure sufficient security by...

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 王菡子刘光禄严严
Owner XIAMEN UNIV
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