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

An expression recognition method based on adaptive weighted fusion of significant structure tensors and LBP features

An adaptive weighting and structure tensor technology, which is applied in the field of image processing and computer vision, can solve the problems of inaccuracy, memory consumption, and failure to find, etc., and achieve the effects of suppressing noise, improving recognition rate, and enhancing texture information

Active Publication Date: 2019-01-08
GUANGDONG UNIV OF TECH
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this method has a high recognition rate, a single feature cannot effectively and comprehensively describe the detailed information of the expression image.
Zheng Yongbin combined SIFT with LBP to obtain a new image description and matching algorithm, but this method has "inaccuracy" and consumes memory
These methods have different advantages compared to traditional LBP, but none of them have found a method that is complementary to LBP to extract more effective and comprehensive features.

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
  • An expression recognition method based on adaptive weighted fusion of significant structure tensors and LBP features
  • An expression recognition method based on adaptive weighted fusion of significant structure tensors and LBP features
  • An expression recognition method based on adaptive weighted fusion of significant structure tensors and LBP features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] An expression recognition method for adaptively weighted fusion of saliency structure tensor and LBP features, such as figure 1 shown, including the following steps:

[0048] S1: Data preprocessing. In the expression database, different expression images are selected to form the training set and test set, and then the snake and GVF models are used to extract the pure face area of ​​the expression image, and the hair, ears, neck, background and other information that interfere with expression recognition are removed. Finally, scale normalization is performed on the image, and the rendering is shown in Figure 2(a).

[0049] In this example, the JAFFE expression library is selected as the experimental data. The expressions in the library are divided into seven types: anger, disgust, fear, happiness, sadness, surprise, and neutral expressions. In this example, 10 images of each type of expression are selected to form a test set, and the rest are used as a training set. I...

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 an expression recognition method based on adaptive weighted fusion of significant structural tensors and LBP features. The method makes the image features contain both texturedetail information and texture structure information by fusing the structural tensor features and LBP features, so that the image features have higher description ability. The results show that this method improves the accuracy of facial expression recognition.

Description

technical field [0001] The invention relates to the fields of image processing and computer vision, and more specifically, relates to an expression recognition method for adaptively weighted fusion of salient structure tensor and LBP features. Background technique [0002] In recent years, expression recognition has attracted widespread attention in the fields of education, psychoanalysis, medicine, and business. Expression recognition is mainly composed of three parts: image preprocessing, feature extraction and classification recognition. In terms of feature extraction, the more commonly used features mainly include color, texture, gradient, depth, etc. The LBP texture feature has been widely used because of its strong robustness to changes in factors such as pose and illumination in face image analysis, and its fast operation speed. However, the traditional LBP only considers the difference between the central pixel and the neighboring pixels, without considering the ma...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62
CPCG06V40/171G06V40/174G06V40/172G06V10/467G06V10/462G06F18/2411G06F18/253
Inventor 张灵董俊兰
Owner GUANGDONG UNIV OF TECH
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