Three-dimensional facial recognition method based on elasticity matching of facial curves

A 3D face and elastic matching technology, applied in the field of 3D face recognition, can solve problems such as excessive calculation

Active Publication Date: 2013-08-14
SOUTHEAST UNIV
View PDF4 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Purpose of the invention: Aiming at the problem that the calculation amount of 3D face recognition is too large and it is sensitive to the influence of expression, occlusion, noise, etc., the present invention provides a method with good recognition performance and better robustness to expression, occlusion and noise. A novel 3D face recognition method based on facial curve elastic matching

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
  • Three-dimensional facial recognition method based on elasticity matching of facial curves
  • Three-dimensional facial recognition method based on elasticity matching of facial curves
  • Three-dimensional facial recognition method based on elasticity matching of facial curves

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0068] The three-dimensional human face recognition method based on facial curve elastic matching of the present invention realizes the three-dimensional human face recognition process with the C++ programming language through the VC++6.0 platform in the Windows operating system. The experimental data comes from the FRGC v2.0 3D face database, collected by the University of Notre Dame in the United States, mainly in the fall of 2003 and the spring of 2004. figure 1 It is an overall flow chart of the inventive method, and the concrete steps are as follows:

[0069] Step 1), respectively preprocessing the test face model and the N library face set models, the preprocessing steps are as follows:

[0070] Step 1.1), cut the original face model to get the face model:

[0071] The original face model is attached figure 2 As shown, the position of...

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 three-dimensional facial recognition method based on elasticity matching of facial curves comprises the following steps: firstly, performing pretreatment on a three-dimensional face, extracting a plurality of facial radial curves emitted from a nose top point, and performing resampling on the radial curves to extract useful points; then, performing layering elasticity matching on all radial curves of the detected face and corresponding curves of faces gathered in a library, and performing point distance matching on the curves according to point corresponding relations established between the detected face and the faces gathered in the library and by using distances between corresponding points and the nose top point; and lastly, performing weighting fusion on layering elasticity matching similarity and point distance matching similarity of the facial radial curves to be used as general similarity for recognition. The three-dimensional facial recognition method provided by the invention has a very good recognition capacity, and has better robustness to expressions, blocking and noises.

Description

technical field [0001] The invention belongs to the field of three-dimensional face recognition, and relates to a three-dimensional face recognition method based on facial curve elastic matching. Background technique [0002] Biometric recognition has important applications in the field of security, especially compared with fingerprint recognition, iris recognition and other biometric recognition technologies, face recognition has the characteristics of non-contact and good concealment, and has become the current trend in the field of pattern recognition and computer vision. Research hotspots. Traditional two-dimensional face recognition based on two-dimensional grayscale or color images has achieved better recognition performance, but it is still susceptible to factors such as lighting, posture, makeup, etc., and three-dimensional face data contains more than two-dimensional face data. information, and will not be affected by posture and illumination, so 3D face recognitio...

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 Applications(China)
IPC IPC(8): G06K9/00
Inventor 达飞鹏潘仁林陶海跻刘健郭涛陈璋雯
Owner SOUTHEAST UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap