Feature point positioning method combined with active shape model and quick active appearance model

A technology of active shape model and feature point location, applied in the field of image processing, can solve the problem of low search accuracy

Inactive Publication Date: 2006-11-22
SHANGHAI RUISHI MACHINE VISION TECH
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention is aimed at the deficiencies in the prior art, proposes a kind of facial feature point localization method combining ASM and Lucas AAM, makes it combine ASM and Lucas AAM (fast active appearance model) two methods together to carry out facial feature point localization , so that the disadvantage of low global se

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
  • Feature point positioning method combined with active shape model and quick active appearance model
  • Feature point positioning method combined with active shape model and quick active appearance model
  • Feature point positioning method combined with active shape model and quick active appearance model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The technical solution of the present invention will be further described in detail below in conjunction with a specific embodiment.

[0033] The images used in the embodiment are from the captured face image library. The whole implementation process is as follows:

[0034] 1. Select 500 face images marked with feature points from the face database to build an ASM model. A face image with marked feature points, such as figure 1 shown. The corresponding 500 shape vectors and texture vectors are processed by principal component analysis to complete the establishment of the Lucas AAM model. In this way, any shape can be expressed as x=x+Pb, and any texture can be expressed as A ( x ) = A 0 ( x ) + Σ i = 1 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 disclosed characteristic point locating method comprises: (1) building Lucas AAM model, calculating initial parameters, and obtaining initial position; (2) building ASM model; (3) searching human face characteristic point by the initial position from (1) and Lucas AAM method; and (4) searching new position by the initial position from (3) and ASM method. This invention makes good use of Lucas AAM and ASM methods, and increases search speed.

Description

technical field [0001] The invention relates to a method in the technical field of image processing, in particular to a feature point positioning method combining an active shape model and a fast active appearance model. Background technique [0002] In recent years, research in the field of human face has attracted more and more attention from scientific researchers, and the location of facial feature points is a key link in the entire field of face research. The accuracy of facial feature point location directly affects subsequent face research. all aspects of. [0003] After searching the prior art documents, it was found that T.F. Cootes et al. published "Active Shape Model-Its Training and Application" in "Computer Vision and Image Understanding" (the first issue of 1995, page 38), the ASM proposed in this paper (Active shape model) method, in this method, when carrying out feature point new position search, find the center of the sub-contour that makes Mahalanobis dis...

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
IPC IPC(8): G06K9/00
Inventor 杜春华杨杰吴证
Owner SHANGHAI RUISHI MACHINE VISION TECH
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