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

Facial Emotion Recognition Method Based on Bayesian Fusion Sparse Representation Classifier

A facial expression recognition and sparse representation technology, applied in the field of pattern recognition, can solve the problem of different contribution of facial features and other parts to recognition, and achieve the effect of high recognition rate, strong classification ability and improved accuracy

Active Publication Date: 2018-10-09
SOUTH CHINA UNIV OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current integration is mostly feature-based integration, and it has not noticed that the contribution of facial features and other parts to the recognition degree is not the same in the process of facial emotion recognition.

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
  • Facial Emotion Recognition Method Based on Bayesian Fusion Sparse Representation Classifier
  • Facial Emotion Recognition Method Based on Bayesian Fusion Sparse Representation Classifier
  • Facial Emotion Recognition Method Based on Bayesian Fusion Sparse Representation Classifier

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0024] Such as figure 1 As shown, the face emotion recognition method based on Bayesian fusion sparse representation classifier, including training part and testing part:

[0025] Include the following steps in the training section:

[0026] The first step: preprocessing. Such as Figure 2a with Figure 2b As shown, the face image is detected by the HAAR cascade classifier and the background area is removed. Normalize the image of the expression area to a grayscale image and normalize it to a size of 64*64, and use histogram equalization to process the image to reduce the influence from the light.

[0027] Step 2: Use the pre-trained ASM algorithm to identify the facial features of the facial expression image, and divide the facial expression image into four parts according to the distribution of facial features according to the hints of the ASM algorithm marking points, corresponding to the forehead, eyes, nose and mouth.

[0028] Step 3: Send the segmented sub-images t...

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 new face emotion recognition method, including preprocessing of face expression pictures, image segmentation, feature extraction, classification and classification result fusion. Divide it into four sub-images (corresponding to the forehead, eyes, nose, and mouth respectively), use the sparse representation classifier to classify the sub-image and the original image respectively to obtain five possible classification results, and finally use the weighted Bayesian fusion decision Theoretically adjust the weight distribution of different facial features, taking into account the similarity and dissimilarity between expressions. It has the advantages of simple practice, strong robustness to noise and occlusion, and can better deal with the complex situation of real facial expression recognition and improve the accuracy of facial expression recognition.

Description

technical field [0001] The invention relates to a pattern recognition technology, in particular to a human face emotion recognition method based on a Bayesian fusion sparse representation classifier. Background technique [0002] As human-computer interaction becomes the craze of the new century, facial emotion recognition is also playing an increasingly important role. Many electronic devices now have a need to improve the ability to understand human emotions. For example: if a nursing robot has the ability to continuously monitor the patient's emotional state, it can give the patient appropriate care and quickly respond to critical situations. In addition, if the owner of the smart home is detected to express negative emotions, the smart home system can choose to play the owner's favorite music or speak positive words in response. [0003] It is precisely because of the wide application of facial emotion recognition that many methods for facial emotion recognition have b...

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
CPCG06V40/174G06V40/172G06V10/513G06F18/285G06F18/2136
Inventor 文贵华李丹扬
Owner SOUTH CHINA UNIV OF TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com