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

A face state recognition method and device based on deep learning

A state recognition and deep learning technology, applied in neural learning methods, character and pattern recognition, acquisition/recognition of facial features, etc., can solve the problem of not extracting feature points, etc., to achieve efficient perception and analysis, efficient human-computer interaction, rich Effects of emotion detection models

Active Publication Date: 2022-08-05
HOHAI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of the fatigue monitoring methods based on image processing only obtain the position below the driver's eyes, and do not further extract feature points for local feature information such as the human eyes.

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 face state recognition method and device based on deep learning
  • A face state recognition method and device based on deep learning
  • A face state recognition method and device based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0104] The invention relates to deep learning technology, which adopts deep neural network and facial feature point processing model information to comprehensively discriminate to analyze the face information of the recognized person, thereby recognizing the seven emotions of the recognized person and the fatigue condition of the recognized person. Based on this information, we can play appropriate music to adjust the mood and fatigue of the identified person. The method includes collecting the image of the recognized person and recording the collection time; using a face recognition algorithm for processing and outputting the face recognition result; inputting the face recognition result into a deep neural network and a feature point processing model for processing to obtain expressions and fatigue. Recognition results; the expression and fatigue recognition results and the corresponding collection time are recorded in the expression and fatigue database in sequence as express...

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 disclosed a method and device based on deep learning. The method includes: collecting the face image of the recognized person and recorded the collection time, and the face recognition algorithm is processed to the recognized person's image.Output human face recognition results.Enter the face recognition results into the deep neural network and the face feature point model of the pre -training to obtain the expression recognition results and fatigue recognition results; the expression recognition results include the type of emoji and its prediction value.The emoticon recognition results and corresponding collection time are recorded as emoji data, recorded in the emoji database; the fatigue data is also recorded in the fatigue database according to time.Obtain multiple data from the expression and fatigue database and analyze it to obtain the status recognition result of the recognized person.The present invention can efficiently perceive and analyze the emotional and fatigue of the recognized person, and can be widely used in automation fields such as fatigue driving testing and robots.

Description

technical field [0001] The invention belongs to the technical field of image recognition processing, and relates to a deep learning-based face state recognition method and device. Background technique [0002] Emotion recognition refers to the study of an automatic, efficient and accurate system to recognize the state of facial expressions, and then to understand people's emotional states, such as happiness, sadness, surprise, anger, etc., through facial expression information. This research has important application value in human-computer interaction, artificial intelligence, etc., and is one of the important topics in the current computer vision, pattern recognition, affective computing and other fields. [0003] In the technical field that requires human-computer interaction, especially in robotics, it is usually necessary to be able to analyze human emotions in order to carry out effective human-computer interaction and bring sensory improvements to the user's interacti...

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): G06V40/16G06V20/59G06V10/764G06V10/82G06N3/04G06N3/08
CPCG06V40/168G06V40/174G06V40/172G06V20/597
Inventor 胡鹤轩周全朱宇航彭守恒刘航朱映恺谭国平冯芸
Owner HOHAI UNIV
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