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

Near infrared human face image identification method based on wavelet theory and sparse representation theory

A sparse representation and image recognition technology, applied in the field of intelligent face image recognition, can solve the problems of strong expressions and complex lighting, and achieve the effect of eliminating the influence, improving the recognition effect and improving the recognition effect.

Inactive Publication Date: 2012-12-19
HUNAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when in a complex recognition environment, such as complex lighting and strong expressions and posture changes, the current method still has great difficulties in the recognition process

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
  • Near infrared human face image identification method based on wavelet theory and sparse representation theory
  • Near infrared human face image identification method based on wavelet theory and sparse representation theory
  • Near infrared human face image identification method based on wavelet theory and sparse representation theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0018] see figure 1 , is a flowchart of the method of the present invention. This method adopts the strategy of learning to realize face recognition. The specific implementation details of each part are as follows:

[0019] (1) Perform wavelet transform on all near-infrared face images to obtain wavelet transform subbands.

[0020] In order to better represent the texture and detail information of the image, the present invention uses wavelet transform on the image to obtain wavelet transform coefficients. see figure 2 , the present invention adopts Daubechies 1 wavelet to do one-layer wavelet decomposition to all face images, and obtain four subbands of approximation, horizontal, vertical and diagonal.

[0021] (2) see image 3 , apply the obtained subbands to construct a sparse representation dictionary. Stack the subbands of the wav...

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 belongs to the technical field of intelligent human face image identification, and in particular relates to a near infrared human face image identification method based on a wavelet theory and a sparse representation theory. The method comprises the following steps of: performing wavelet transform on a near infrared human face image to obtain four approximate, horizontal, vertical and diagonal sub-bands; constructing a sparse representation dictionary by using the sub-bands; respectively performing sparse representation on each wavelet sub-band corresponding to the human face sample image to be identified according to the dictionary, and solving; performing class correlation processing on a sparse coefficient obtained by the sparse representation, and comparing with the original signal to obtain residual sum; and obtaining an identification result by taking the residual sum as a sorting basis. The method can obviously improve human face identification accuracy and achieves ideal identification effect by combining the wavelet theory with the sparse representation theory.

Description

technical field [0001] The invention belongs to the technical field of intelligent face image recognition, and in particular relates to a near-infrared face image recognition method based on wavelet and sparse representation theory. Background technique [0002] With the rapid development of intelligent computer technology, face recognition has become one of the most concerned issues in the field of pattern recognition in recent years. Face recognition has high academic research value and broad commercial application prospects. Face recognition methods mainly include: methods based on geometric features, methods based on template matching and methods based on learning. The method based on geometric features is more in line with the cognitive mechanism of human beings and is not sensitive to changes in illumination, but it has a greater impact on the algorithm when it is occluded or there are strong changes in expression and posture. The method based on template matching ha...

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): G06K9/00G06K9/64
Inventor 李树涛魏丹
Owner HUNAN 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