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

Multi-view microexpression recognition method and device, storage medium and computer device

A recognition method and micro-expression technology, applied in the field of image recognition, can solve the problems of inability to meet the needs of multi-angle and multi-pose micro-expression recognition, poor recognition of multi-pose expressions, low accuracy of expression recognition, etc., and achieve multi-angle and multi-pose The effect of micro-expression recognition needs

Pending Publication Date: 2019-01-08
ONE CONNECT SMART TECH CO LTD SHENZHEN
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the existing facial expression recognition models are mainly based on the recognition of changes in frontal facial expressions, and are poor in multi-pose facial expression recognition. The recognition of the above six basic expressions cannot meet the needs of multi-angle and multi-posture micro-expression recognition, and the accuracy of expression recognition is low

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
  • Multi-view microexpression recognition method and device, storage medium and computer device
  • Multi-view microexpression recognition method and device, storage medium and computer device
  • Multi-view microexpression recognition method and device, storage medium and computer device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] An embodiment of the present invention provides a multi-view micro-expression recognition method, such as figure 1 As shown, the method includes:

[0048] Step S101: Obtain the expression data of the user's target expression, the expression data includes the person's expression images of the target expression at multiple angles.

[0049] For this embodiment, the acquired expression data is specifically the expression data of the user's target expression collected based on multiple angles, wherein the multiple angles include: front view, top view, left view and right view four angles . The expression data specifically include facial expression images from four angles: front view, top view, left view, or right view. The expression images of characters can be photos, video frames extracted from real-time videos or video files, etc. The present invention The embodiment does not limit this.

[0050]For this embodiment, the target expressions include but are not limited to...

Embodiment 2

[0061] Another possible implementation of the embodiment of the present invention, on the basis of the first embodiment, further includes the steps shown in the second embodiment, wherein,

[0062] The micro-expression recognition model in the step S102 includes: a preset convolutional neural network (CNN) for extracting the expression features of the expression data and a long Short-term memory neural network LSTM.

[0063] For this embodiment, the preset micro-expression recognition model is a micro-expression recognition model trained based on a convolutional neural network CNN (Convolutional Neural Network) and a long-short-term memory neural network LSTM (Long Short-Term Memory), that is, the The micro-expression model integrates convolutional neural network CNN and long-term short-term memory neural network LSTM to realize expression classification. Wherein, the convolutional neural network CNN plays the role of expression feature extraction in the micro-expression reco...

Embodiment 3

[0070] Another possible implementation of the embodiment of the present invention, on the basis of the first embodiment, further includes the steps shown in the third embodiment, wherein,

[0071] Such as figure 2 As shown, the micro-expression recognition model in the step S102 is trained through the following steps:

[0072] Step S201: Obtain expression data and corresponding expression classifications of target expressions of historical users, the expression data includes person expression images of target expressions at multiple angles.

[0073] For this embodiment, the expression data of the historical user's target expression and the expression classification corresponding to the expression data are used to train the micro-expression recognition model, wherein the expression data includes the historical user's target expression at multiple angles The facial expressions of the characters below.

[0074] For this embodiment, the multiple angles include four angles: fron...

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 provides a multi-view micro-expression recognition method and device, a storage medium and a computer device. The method comprises the following steps: obtaining facial expression data of a target expression of a user, wherein the facial expression data includes figure expression images of a target expression at multiple angles; inputting the expression data of the user into a plurality of preset microexpression recognition models to obtain a set of expression classification probabilities corresponding to each microexpression recognition model, wherein the set of expression classification probabilities comprises a matching probability between the expression data and different expression classifications; calculating an average value of matching probabilities of the same expression classification in each expression classification probability set; determining the expression classification corresponding to the target expression according to the average value of the matching probability of the expression classification. This method can quickly and accurately realize multi-angle multi-pose micro-expression recognition, and meet the needs of multi-angle multi-pose micro-expression recognition.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular, the present invention relates to a multi-view micro-expression recognition method, device, computer-readable storage medium and computer equipment. Background technique [0002] With the rapid development of computer technology, facial expression recognition technology, which can be applied to human-computer interaction, pattern recognition, psychological research and other fields, has become one of the current important scientific research directions. Among them, most of the research is aimed at the expression recognition method of the six basic expressions of happiness, sadness, surprise, disgust, anger and fear. In order to improve expression recognition efficiency as much as possible and obtain better expression recognition results, various improved expression recognition models emerge in endlessly. [0003] However, the existing facial expression recognition...

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
IPC IPC(8): G06K9/00G06K9/46G06K9/62
CPCG06V40/174G06V40/172G06V40/168G06V10/449G06F18/24
Inventor 胡艺飞徐国强邱寒
Owner ONE CONNECT SMART TECH CO LTD SHENZHEN
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