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

A face recognition method

A face recognition and face image technology, applied in the field of face recognition, can solve the problems of face recognition performance degradation

Active Publication Date: 2019-08-16
WUHAN INSTITUTE OF TECHNOLOGY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The present invention provides an extreme learning machine robust face recognition algorithm based on low-rank support to solve the problem of face recognition performance in complex application scenarios due to interference from factors such as illumination changes, occlusions, and noise changes. Reduced technical issues

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 face recognition method
  • A face recognition method
  • A face recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] In order to enable those skilled in the technical field to which the application belongs to understand the application more clearly, the technical solutions of the application will be described in detail below through specific embodiments in conjunction with the accompanying drawings.

[0048] In an embodiment of the present invention, a face recognition method is disclosed.

[0049] S1, extract P face images in the face collection, divide the remaining images in the face collection into n types of face images as a training sample library, and then use the category mean information in the training sample library to pair The P face images are pre-classified. P is a positive integer, and n is a positive integer.

[0050] In the specific implementation process, first obtain P faces from the face collection, and P is a positive integer.

[0051] The jth face image: x j ∈ R d×1 , j=1,2,3,...,p, that is, there are P faces in total. R d×1 Represents a matrix, dx1 represe...

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 discloses a face recognition method, which extracts p face images from a face set, divides the remaining images in the face set into n types of face images and uses them as a training sample library, and adopts the training sample library Pre-classify P face images based on the category mean information of P, and perform low-rank restoration on each image in P face images and images of corresponding categories after classification, to obtain low-rank restored images and sparse error images. Based on the principle that the low-rank nature of low-rank images is robust to noise, the extreme learning machine is trained using the training sample library, and finally the low-rank restored image corresponding to P face images is used as the test sample library, and the extreme learning machine is used as the standard to establish P The mapping relationship between the face image and the face label obtained after training, and the face recognition of the low-rank restored image corresponding to the P face image not only improves the robustness of the recognition of the extreme learning machine, but also reduces the computational complexity. Spend.

Description

technical field [0001] The present application relates to the technical field of automatic face image recognition, and in particular to a face recognition method. Background technique [0002] Face recognition is widely used in various fields such as information security and public safety. It has always been a hot topic in computer vision and pattern recognition, and has extremely high theoretical research and application value. [0003] The face recognition algorithm mainly derives its corresponding identity information from the input face image. Generally speaking, the face recognition algorithm is mainly divided into four steps: pre-processing, sign extraction, encoding and classification. Around these four links, a large number of literatures have carried out research work in the field of face recognition in recent years, and achieved good results. [0004] Benefiting from the theoretical development of computer vision, a large number of manually designed image feature...

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
CPCG06V40/168G06V40/172
Inventor 卢涛管英杰张彦铎李晓林万永静杨威潘兰兰汪浩
Owner WUHAN INSTITUTE OF TECHNOLOGY
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