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

Human face recognition method based on human face statistics

A technology of face recognition and knowledge, applied in the field of identity recognition based on face images, can solve problems such as impractical and time-consuming

Inactive Publication Date: 2006-05-24
FUDAN UNIV
View PDF0 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because it needs to optimize the shape and texture at the same time, it is time-consuming and easy to fall into the local minimum, and the initial feature point position needs to be obtained manually, which is not practical at present.

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 based on human face statistics
  • Human face recognition method based on human face statistics
  • Human face recognition method based on human face statistics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment example

[0080] Taking a large-scale human face image database as an example, the implementation process of this method will be described below. The face image library in this example contains 2000 Chinese faces, each with three images of -30°, 0° and 30°. Figure 5 Three images of the same person are shown. Our 3D deformable face model comes from the 3D face data of 60 Chinese people. These data are obtained by optical synthesis of photos taken by two cameras. After preprocessing and registration, each face data contains 26498 vertices. In the end, we took 9 shape feature vectors, and manually calibrated 60 feature points on the model, such as figure 2shown. The implementation process is as follows:

[0081] 1. Training stage:

[0082] A) LDA gesture recognition base:

[0083] We divide the poses into three intervals of -30°, 0° and 30°, and use 200 face sub-images detected by the Adaboost method for each type of pose as a sample training base for LDA pose recognition. The out...

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

Using registered one piece of frontal normal personí»s face image, the method can obtain virtual images of the personí»s face at different postures. Further, using recognition strategies including separated two stages of posture recognition and identity recognition, the method solves issue between registered image and changed postures of personí»s face at time of recognition. The method includes: 3D deformable model of personí»s face for representing structural statistical information of personí»s face; reconstruction algorithm for reconstructing 3D personí»s face from frontal personí»s face image, and two stages of posture recognition and identity recognition. Under condition of only one registered frontal normal personí»s face image, the invention still obtains higher recognition rate from side test images.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition, and in particular relates to an identity recognition method based on a face image. technical background [0002] Although face recognition has been studied for decades, it is still a very challenging problem in the field of pattern recognition. Two-dimensional based methods have made great progress in the past research, including Eigenface[1], Fisherface[2], and AAM[3] and so on. However, there are still a series of difficult problems in the face recognition method based on two dimensions. For example, when the face posture, expression and ambient illumination (PIE) change greatly, the recognition rate of the system will drop sharply. How to solve the problem of face recognition under different postures, lighting and expression conditions is still a hot spot of current research. [0003] For the face recognition problem with pose changes, the traditional method must obtain enough fa...

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 姜嘉言张立明
Owner FUDAN 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