A method of facial feature localization based on facial features-related AAM model

A positioning method and facial feature technology, applied in computer parts, character and pattern recognition, instruments, etc., can solve problems such as enhancing the robustness of feature positioning algorithms and affecting the accuracy of feature positioning algorithms.

Inactive Publication Date: 2011-12-07
WUHAN UNIV
View PDF2 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention mainly solves the technical problems existing in the prior art that rely on the result of face region detection, if the face detection result is inaccurate or fails, it will directly affect the accuracy of the feature locatio

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
  • A method of facial feature localization based on facial features-related AAM model
  • A method of facial feature localization based on facial features-related AAM model
  • A method of facial feature localization based on facial features-related AAM model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0096] Below in conjunction with accompanying drawing, the present invention will be further described with specific embodiment:

[0097] 1. Training facial features related AAM model based on sample image set

[0098] (1) Select a group of face image sample data as the training set (take the internationally open standard IMM face database as an example), and manually mark the face features on the sample images. There are 58 feature points in total, which are the left and right eyes 8, 5 each for the left and right eyebrows, 11 for the nose, 8 for the mouth, and 13 for the facial contours.

[0099] (2) Delaunay triangulation is performed based on the manually marked feature point set, and the face area is divided into five organs including left eye, right eye, nose, mouth, and facial contour.

[0100] The shape model S can therefore be expressed as a combination of facial features, that is, S=(S eyeL , S eyeR , S nose , S mouth , S outline ), where the triangular mesh co...

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 facial feature location method aiming at partially obscured images in complex scene. The method comprises the following steps of: based on a sample image set, respectively modeling for each facial organ, and training to obtain an AAM (Active Appearance Model) related to the five sense organs; determining search areas of the AAM through a Haar feature face detection technology while initially locating a facial area, and classifying the search areas according to the probability of being searched; at an AAM fitting calculation part, respectively performing error calculation for each facial organ based on an obscuring weight of the five sense organs, and then, comprehensively evaluating a fitting degree of the model and the image through an energy function; and performing search optimization on a fitting process of the AAM by a genetic algorithm. In comparison with the prior related algorithms, the method can locate the facial features of the partially obscured images more accurately, and can enhance the robustness of the algorithms and improve the efficiency of the algorithms while ensuring higher accuracy.

Description

technical field [0001] The invention relates to the technical field of face image facial features detection and positioning based on digital image processing and pattern recognition, in particular to a facial feature positioning method based on facial features-related AAM models. Background technique [0002] Face recognition technology is one of the most difficult research topics in the field of biometrics and even in the field of artificial intelligence by analyzing and comparing the visual feature information of faces. The difficulty of face recognition mainly comes from the characteristics of faces as biometrics. A popular field of study in computer technology. [0003] The main methods of model-based face recognition include Active Shape Model (ASM) and Active Appearance Model (AAM). ASM uses the shape information of the object to learn and train the model of shape change, and then searches for the target in the image with the help of the trained model. Although ASM u...

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): G06K9/66
Inventor 赵俭辉李磊袁志勇
Owner WUHAN 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