Facial expression recognition method based on Intra-Class Gap GAN

A technology of facial expression and recognition method, which is applied in character and pattern recognition, acquisition/recognition of facial features, computer components, etc., which can solve problems that are difficult and cannot meet the recognition rate of facial expression recognition, and achieve the effect of small difference

Pending Publication Date: 2021-01-05
SHENYANG LIGONG UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] According to the intra-class gap in facial expression recognition in the real situation proposed above, in view of the difficulty in security inspection in complex environments, the technical problems caused by the intra-class gap that cannot meet the requirements of facial expression recognition recognition rate, provide a method based on generative confrontation facial expression recognition method

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 expression recognition method based on Intra-Class Gap GAN
  • Facial expression recognition method based on Intra-Class Gap GAN
  • Facial expression recognition method based on Intra-Class Gap GAN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0124] A facial expression recognition method based on Intral-Class Gap GAN,

[0125] The construction of the recognition model includes the following steps:

[0126] (1) Collect real-time images of different sources and expressions of human faces;

[0127] (2), the image is input to the Intral-Class Gap GAN neural network model for identification;

[0128] (3), output recognition results;

[0129] The Intral-Class Gap GAN neural network model construction method in the described (2) step is as follows:

[0130] (2.1), collecting historical images of different sources and expressions of human faces;

[0131] (2.2), preprocessing the collected face images, constructing a facial expression data set;

[0132] (2.3), there is an intra-class gap in the data set in (2.2) (the gap of the same expression is called the intra-class gap, or the same kind of expression has different expression forms, this type is the intra-class gap, and it can be called the intra-class gap The gap 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 facial expression recognition method based on Intra-Class Gap GAN, and the method comprises the following steps: (1), collecting the real-time images of different sources anddifferent expressions of a human face; (2) inputting the image into an Intra-Class Gap GAN neural network model to carry out recognition; and (3) outputting a recognition result. According to the generative adversarial-based facial expression recognition method provided by the invention, compared with a traditional artificial expression feature extraction method, automatic extraction of facial expression features is realized, and compared with slightly early neural network facial expression recognition, the recognition rate is improved, so that expression recognition is accurately carried out.

Description

technical field [0001] The present invention relates to the field of facial expression recognition of image processing and deep learning, generally speaking, it relates to a facial expression recognition method based on generative confrontation. Background technique [0002] my country's huge floating population poses enormous pressure on urban infrastructure and public services. In recent years, vicious injuries have occurred frequently. Facial expression recognition becomes particularly important. Expression is the emotional state shown by facial muscle changes. Through the recognition of human facial emotional expression, abnormal psychological states can be judged, extreme emotions can be judged, and facial expressions of pedestrians in complex environments can be observed to further judge human psychology. Provide technical support, roughly determine who is more suspicious, and prevent certain criminal activities in time. Traditional facial expression recognition is 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): G06K9/00G06K9/62G06N3/04
CPCG06V40/174G06V40/172G06V40/161G06V40/168G06N3/045G06F18/214
Inventor 刘韵婷陈亮吴攀
Owner SHENYANG LIGONG UNIV
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