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

Corresponding three-dimensional face recognition method based on dense point

A technology of 3D face and recognition method, applied in the field of 3D face recognition, can solve the problems affecting the performance of 3D face recognition, many interference areas, and large amount of calculation

Active Publication Date: 2012-04-11
海安江理工技术转移中心有限公司 +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the amount of 3D face data is large, there are many interference areas, and the amount of calculation is large, and the non-rigid deformation of the face surface due to expressions affects the performance of 3D face recognition based on geometric information.

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
  • Corresponding three-dimensional face recognition method based on dense point
  • Corresponding three-dimensional face recognition method based on dense point
  • Corresponding three-dimensional face recognition method based on dense point

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] With reference to the accompanying drawings in the description, the specific embodiments of the present invention are described in detail below:

[0035] 1. Kuji 3D face model preprocessing

[0036] The preprocessing is divided into three steps: convert the face model to the face axis coordinate system, cut the face, obtain 13 control points of the 3D face model, and obtain 13 average marker points of the Kuji face model.

[0037] (1) Determine the main axis coordinate system of the face and cut the face

[0038] The face model is approximated as an ellipsoid with a long vertical direction, a middle left and right span, and a small front and rear thickness. Doing the principal component analysis (Principle Component Analysis) on the face point set distribution, you can get three eigenvectors, these three eigenvectors correspond to the three eigenvalues ​​sorted from large to small, according to the relationship between the eigenvalues ​​and eigenvectors of PCA , the m...

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 relates to a corresponding three-dimensional face recognition method based on dense point, comprising the following steps: (1) a library-stored three-dimensional face model is pre-processed, average signalized point is solved. (2) A thin plate spline function is utilized to lead all the library-stored faces to be deformed to the average signalized point. (3) One deformed library-stored face is selected and is thinned to obtain a reference face model. (4) The deformed library-stored face is matched with the reference face to obtain a thinning model, and then the point corresponding to sequence number is found in the un-deformed library-stored faces, thereby obtaining an un-deformed thinning model which is used as the final library-stored face model. (5) When a tested face model enters in, the tested face model is processed like the library-stored faces, and an un-deformed thinning tested face is obtained as the final tested face model. (6) point-group distance between thetested face and the library-stored face is used as similarity, a model, closest to the point-group distance of the final tested face model, is selected as the recognition result in the final library-stored face models.

Description

technical field [0001] The invention relates to a three-dimensional face recognition method, which adopts thin-plate spline deformation and dense point correspondence, and reduces the influence of expression and face size inconsistency on recognition. Background technique [0002] Biometric identification has important applications in the field of security, especially compared with fingerprints, irises and other features, automatic face recognition technology has attracted more and more attention due to its advantages of non-contact, high acceptability, and good concealment. , has huge room for development. [0003] The traditional face recognition technology based on two-dimensional photos is greatly affected by factors such as lighting, posture, and makeup. Three-dimensional face recognition technology can overcome or alleviate the influence of these factors. A 3D face model has richer information than a 2D image, and it is a more accurate description of the real shape o...

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): G06K9/62G06K9/00
Inventor 达飞鹏张永泽李晓莉
Owner 海安江理工技术转移中心有限公司
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