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

Human face recognition method for eliminating effect of local obstruction

A face recognition, partial occlusion technology, applied in neural learning methods, character and pattern recognition, computer parts and other directions, can solve the problem of poor reconstruction effect of occluders, and achieve the effect of good face reconstruction and good robustness

Inactive Publication Date: 2017-12-12
JILIN UNIV
View PDF2 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the discontinuity of the occlusion, this method has a poor reconstruction effect on the extreme occlusions of sunglasses and scarves.

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 for eliminating effect of local obstruction
  • Human face recognition method for eliminating effect of local obstruction
  • Human face recognition method for eliminating effect of local obstruction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] Specific embodiments of the present invention will be described below in conjunction with the accompanying drawings, so that those skilled in the art can better understand the present invention.

[0048]The present invention performs preliminary identification on the improved BP neural network according to the unoccluded part, and performs identification after fusion of the initially identified human face and the human face to be tested, such as figure 1 Shown is the basic framework of the present invention, and the concrete implementation of this method is described from four aspects:

[0049] 1. Select the AR face database, and form the face database of this experiment from different targets, sunglasses and scarf occluders;

[0050] 2. Image preprocessing: select face images without occlusions from the AR face database as training samples, and other face images with sunglasses and scarves occlusions as test samples, and read face image training samples X i (i=1,2,......

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 human face recognition method for eliminating an effect of a local obstruction belongs to the technical field of artificial intelligence and mode recognition. The method comprises: based on a BP neural network algorithm, performing preliminary human face recognition according to a local feature; then in an RGB space, performing image fusion and reconstruction on a preliminarily recognized human face image and a to-be-recognized human face to remove an obstruction; and finally, performing human face classification recognition on a fused image by using a linear discriminant analysis method and a nearest neighbor classifier. By the method, the obstructed human face can be more effectively recognized and the human face can be better reconstructed compared with the existing method, so that the method is more applicable to human face recognition in a natural environment, and has higher robustness.

Description

technical field [0001] The invention belongs to the field of artificial intelligence and pattern technology, and specifically relates to a recognition method based on reconstructing human faces by eliminating the influence of local occluders. Background technique [0002] Face recognition is one of the most active and challenging problems in artificial intelligence, and has broad application prospects in the fields of network technology, information security, and identification. Face recognition is a frontier hotspot of interdisciplinary research, involving knowledge and technologies of multiple disciplines, such as signal processing, intelligent control, pattern recognition, machine vision, etc. Therefore, the development of face recognition technology puts forward new requirements for many aspects of these disciplines and further drives their development. [0003] In recent years, various face detection methods based on simple backgrounds have been quite mature, and face ...

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): G06K9/00G06N3/08
CPCG06N3/084G06V40/172
Inventor 王世刚王婷李木子赵岩韦健
Owner JILIN 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