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

Diverse facial expression recognition method based on low-rank tensor decomposition

A tensor decomposition and diverse technology, applied in the field of facial expression recognition, can solve the problems of difficult to retain the nonlinear feature changes of expressions, and the expressions are easily affected by different individuals, so as to improve the recognition rate of facial expressions and the ability to express them. Effect

Active Publication Date: 2022-07-29
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

That is, the same kind of expression is easily affected by different individuals, and in the research of practical application, the change information of expression features has two characteristics of nonlinearity and continuity, and it is difficult for traditional dimensionality reduction technology to preserve the change of nonlinear characteristics of expression

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
  • Diverse facial expression recognition method based on low-rank tensor decomposition
  • Diverse facial expression recognition method based on low-rank tensor decomposition
  • Diverse facial expression recognition method based on low-rank tensor decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and accompanying drawings.

[0017] The present invention proposes a schematic diagram of the overall framework of a method for identifying diverse facial expressions based on low-rank tensor decomposition. figure 1 shown.

[0018] The present invention provides a facial expression recognition method, comprising the following steps:

[0019] Perform steps S1 to S5 for the sample set and test set respectively:

[0020] S1: Image preprocessing, using face detection algorithm to intercept the face area in the image;

[0021] S2: Feature extraction, which extracts features from facial expression images through feature operators in multiple modes;

[0022] S3: Tensor modeling, according to the extracted operator features of the face region, construct a tensor model based on o...

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 present invention provides a low-rank tensor decomposition-based multiple face expression recognition method, including image preprocessing steps, feature extraction steps, tensor modeling steps, low-rank learning steps, tensor decomposition steps, and feature classification steps. The invention uses the tensor to represent the feature space and can retain the nonlinear characteristics of the image; the low-rank tensor decomposition technology is used to learn the regional features of the face subspace of different individuals, and the face information in different dimensions is obtained, and then all the subspaces are analyzed. The lower tensor is decomposed, and the effective representation of the expression features is obtained by clustering and reconstruction, and the ability to express facial expression information is stronger, thereby improving the recognition rate of facial expression.

Description

technical field [0001] The invention relates to the technical field of facial expression recognition, in particular to a method for recognizing diverse human facial expressions based on low-rank tensor decomposition. Background technique [0002] In the daily communication of human beings, only 7% of the information is conveyed through language, while the information conveyed by facial expressions is as high as 55%. Studying how computers can understand and express emotions like humans, and can adapt to the environment autonomously, will fundamentally change the connection between people and computers. Therefore, facial expression recognition has broad application prospects. First, it can promote the development of many topics such as human-computer interaction, artificial intelligence, psychology, and computer vision. [0003] The main goal of facial expression recognition is to obtain the common points of people on the same expression, but there is a lot of information in...

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): G06V40/16
CPCG06V40/172G06V40/168G06V40/174
Inventor 刘欣刚李辰琦卓欣然汪卫彬
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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