Unlock instant, AI-driven research and patent intelligence for your innovation.

Three-dimensional face recognizing method weakening influence of expression changes

A technology of 3D face and recognition method, applied in the field of 3D face recognition, can solve the problems of reducing the performance of 3D face recognition and face plastic deformation

Active Publication Date: 2008-02-27
ZHEJIANG UNIV
View PDF0 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the expression change changes the shape of the 3D face model, causing plastic deformation of the local area of ​​the face, which greatly reduces the performance of 3D face recognition. Therefore, how to overcome or reduce the influence of expression is a key in 3D face recognition. problems and challenges
Existing technologies are still unable to achieve better recognition performance under various expression changes

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 face recognizing method weakening influence of expression changes
  • Three-dimensional face recognizing method weakening influence of expression changes
  • Three-dimensional face recognizing method weakening influence of expression changes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] 3D Face Model Pose Positioning

[0057] Pose localization is completed in three steps. First, detect the symmetry plane and extract the silhouette, then determine the nose tip and nose base point, and finally apply a rigid transformation to place the 3D face model in a unified coordinate frame to complete the pose localization.

[0058] (1) Symmetrical surface detection and silhouette extraction

[0059] We first propose a method for robust 3D face symmetry detection. Vertex set V of a given face mesh M M ={p i ∈ R 3 |1≤i≤N}, for any plane, V can be found M Set of mirrored vertices about the plane V M m = { p i m ∈ R 3 | 1 ≤ i ≤ N } , V M any point in p i The corresponding mirror point is V M m p in i m , the to...

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 discloses a kind of method to recognize the 3D face which can lighten the effect of expression shape change. Its steps is: (1) allocating the attitude of the 3D-face model; (2) rigid constraint calculation; (3) restrictive shape change basing on guild; (4) matching the shape-changed intermediate model and the known model in the gallery base to finish recognizing 3D face. The invention can lighten the effect of expression shape change, and improve the performance to recognize 3D face.

Description

technical field [0001] The invention relates to a three-dimensional face recognition method, in particular to a three-dimensional face recognition method based on guided deformation and deformation rigid constraints, which weakens the influence of surface changes and improves recognition performance. Background technique [0002] Automatic face recognition technology has broad application prospects in the fields of national security, military security, public safety, and home entertainment. In the past few decades, face recognition has been extensively studied. However, the image-based 2D face recognition technology still faces great challenges, and the accuracy of 2D face recognition is far from satisfactory under the condition of changing light, posture and expression. [0003] Three-dimensional face recognition technology is expected to fundamentally solve the problem of "affected by posture, light and expression" faced by image-based face recognition methods. Based on t...

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): G06K9/00G06K9/62
Inventor 潘纲王跃明吴朝晖
Owner ZHEJIANG UNIV