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

Human face identifying method based on structural principal element analysis

A technology of face recognition and principal component analysis, which is applied in the field of face recognition to reduce space complexity and facilitate programming

Inactive Publication Date: 2008-10-01
SUN YAT SEN UNIV
View PDF1 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the pivots of the 2DPCA method and the pivots of the PCA method are the eigenvectors of the covariance gap matrix, how to construct the covariance gap matrix and how to calculate the pivot feature of the image (the image's position on the subspace formed by the principal element) projection) is very different

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 identifying method based on structural principal element analysis
  • Human face identifying method based on structural principal element analysis
  • Human face identifying method based on structural principal element analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] specific implementation plan

[0033] Taking the FERET face bank as an example, the implementation process of the present invention is described. There are 1209 pictures of people in the original FERET database, with a total of 14051 images. Select some frontal faces in the FERET face database as training and testing samples, and finally select 70 people, each with 6 pictures, a total of 420 pictures constitute the training and testing sample set. The implementation process is as follows:

[0034] Step 1: Image Preprocessing

[0035] Image preprocessing includes light compensation, histogram equalization, gray scale normalization, etc. After preprocessing, the light distribution of all images is unified to the standard level, eliminating the impact of light differences on face recognition.

[0036] (1) Light compensation

[0037] Since the face recognition method based on PCA is sensitive to light changes, whether the light distribution on the face is uniform has a ...

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 pattern recognition technology area. The invention consists of following key steps: geometric warping, image block, two-dimensional principal component analysis (2DPCA) and similarity coefficient weighted adjustment. The invention performs geometric warping with eyes and mouse as benchmark. After the geometric warping, all face images are the same size, the positions of face various parts in the facial image are fixed, and after the image blocking, the human face local area contained in each block is fixed. The invention uses 2DPCA method to calculate main element and main feature of each image block. The similarity of two images is the distance between their main features, and the similarity is the weighted sum of the similarities of total image blocks. By adjusting the number of main elements and weighted coefficients of similarity of each image block, one can highlight or suppress roles of some pieces in the human image in face recognition.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition, and in particular relates to a face recognition method combining a two-dimensional principal component analysis method (2DPCA) with local features of a face image. technical background [0002] In some special applications of face recognition (such as public security criminal investigation business), we often encounter incomplete face images, for example: [0003] ●Face collages or portraits based on the dictation of eyewitnesses. Witnesses are often only impressed by certain parts of the face (such as eyes, nose, etc.), and have a vague or even no impression of other parts. Therefore, only some areas of face mosaics or portraits produced based on eyewitness accounts are more realistic. [0004] ●Photos of faces with parts of the face covered or plastic surgery done. In order to avoid being chased by the public security organs, criminals often cover their faces as much as possible ...

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 马争鸣胡海峰程永张成言邓娜
Owner SUN YAT SEN 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