A facial expression recognition method in natural scenes based on au symbiotic relationship constraints

A technology of symbiotic relationship and expression recognition, applied in neural learning methods, character and pattern recognition, acquisition/recognition of facial features, etc., can solve problems such as difficult emotional computing

Active Publication Date: 2021-09-10
廊坊市美印信息科技有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the diversity of emotional data captured in natural scenes, affective computing is still a difficult problem.

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 facial expression recognition method in natural scenes based on au symbiotic relationship constraints
  • A facial expression recognition method in natural scenes based on au symbiotic relationship constraints
  • A facial expression recognition method in natural scenes based on au symbiotic relationship constraints

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0026] The flowchart of the method of the present invention is as figure 1 As shown, it specifically includes the following steps:

[0027] Step 1, AU acquisition of face image sequence.

[0028] Step 1.1, read the face image sequence, and locate the facial feature points for each image in the sequence.

[0029] Read each face picture sequentially, and determine the position information of 68 feature points of the face in each picture. Among them, the specific positions of 68 face feature points are as follows: figure 2 shown.

[0030] In step 1.2, the position of the AU is obtained according to the localized face feature points.

[0031] Since this method involves a total of 13 AUs, their distribution on the face 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 a method for recognizing facial expressions in natural scenes based on AU symbiotic relationship constraints, which belongs to the technical field of digital image processing and computer vision. The training of facial expression recognition model. It specifically relates to facial expression recognition methods in natural scenes based on AU symbiotic relationship constraints. The present invention replaces the feature extraction of the entire face image in the facial expression recognition process with local AU feature extraction of the face image by utilizing the research results of anatomy, which greatly reduces the work of feature extraction and reduces the The influence of irrelevant facial features on expression recognition; using the symbiotic relationship between AUs and the symbiotic relationship between AUs and expressions as constraints in the recognition model training process is more reasonable than the previous training of recognition models using data alone.

Description

technical field [0001] The invention belongs to the technical field of digital image processing and computer vision, and in particular relates to a facial expression recognition method in natural scenes based on AU symbiotic relationship constraints. Background technique [0002] Emotion plays an extremely important role in people's daily life. It reflects people's thinking activities and inner feelings, and can further affect people's behavioral responses. Among the various expressions of human emotions, facial expressions play an important role in conveying people's own emotions and psychological feelings. Applying the cognition of human emotion to human-computer interaction is conducive to improving the naturalness of human-computer interaction and improving the ability to serve natural people. It has broad application prospects in the fields of intelligent service robots, education, social security, and game entertainment. However, affective computing is still a difficu...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V40/171G06V40/174G06N3/045
Inventor 贾熹滨王悦宸李威庭苏醒郭黎敏
Owner 廊坊市美印信息科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap