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

A 3D Face Recognition Method Based on Probabilistic Graphical Model

A technology of probabilistic graph model and 3D face, which is applied in the field of 3D face recognition based on probabilistic graph model, can solve problems such as increasing intra-class distance, affecting recognition rate, difficulty in 3D face recognition with facial muscles, etc. The effect of small computational complexity and improved robustness

Active Publication Date: 2018-08-07
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, the stretching and contraction of facial muscles caused by the change of expression has caused great difficulties for 3D face recognition. The change of expression increases the intra-class distance to a certain extent and affects the recognition rate.

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 3D Face Recognition Method Based on Probabilistic Graphical Model
  • A 3D Face Recognition Method Based on Probabilistic Graphical Model
  • A 3D Face Recognition Method Based on Probabilistic Graphical Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0023] Such as figure 2 As shown, the present invention mainly relates to the two stages of modeling and model matching of the three-dimensional human face probability map model, and the main implementation process is as follows:

[0024] 1. The original 3D face data contains a series of irrelevant organs such as hair and ears, with different poses and some noise. Therefore, firstly, the rough outline of the face is cut based on the tip of the nose; then, the posture is adjusted based on the axis angle description method to register the 3...

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 three-dimensional human face recognition method based on a probability graph model. The method uses three-dimensional geodesic lines to determine a feature point model and locates the feature points of the three-dimensional human face to be measured; uses Gabor wavelet to extract the neighborhood features of the feature points; Construct an "elastic" 3D face probabilistic graphical model, and use the probabilistic graphical model to classify and recognize 3D human faces. This method has high recognition accuracy, especially strong robustness to facial expression changes, and has low computational complexity. This has important theoretical and practical significance for the research of face recognition and the development of practical applications.

Description

technical field [0001] The invention relates to a three-dimensional human face recognition method based on a probability graph model, in particular to a method for effectively recognizing a three-dimensional human face by modeling a probability graph on a three-dimensional human face, belonging to computer graphics, digital image processing and Artificial intelligence technology field. Background technique [0002] Face recognition has important application prospects and practical value whether it is in the fields of national security, military security, and public security, or in the fields of civil and economic fields, and home entertainment. Compared with two-dimensional faces, three-dimensional faces are more adaptable to factors such as illumination, viewing angle, and occlusion, making face information richer and more accurate. [0003] At present, most mainstream 3D face recognition algorithms start from geometric features, local features and overall features to reco...

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 Patents(China)
IPC IPC(8): G06K9/00
CPCG06V40/171G06V40/172
Inventor 周大可陈志轩杨欣黄经纬
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS