A video sequence expression recognition method based on mixed deep learning

A video sequence and facial expression recognition technology, which is applied in character and pattern recognition, acquisition/recognition of facial features, instruments, etc., can solve problems such as dynamic changes in video sequences that are not considered

Pending Publication Date: 2019-01-11
TAIZHOU UNIV
View PDF0 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, when the above-mentioned literature uses deep learning technology for video sequence expression recognition, it only considers the spatial features of static images in the video sequence, and does not take into account the dynamic changes in the video sequence that are helpful for expression recognition, such as light. stream information

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 video sequence expression recognition method based on mixed deep learning
  • A video sequence expression recognition method based on mixed deep learning
  • A video sequence expression recognition method based on mixed deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0064] figure 1 The block diagram of this system mainly includes:

[0065] Step 1: preprocessing of video sequences;

[0066] Step 2: Using spatio-temporal convolutional neural network to extract spatio-temporal features of video clips;

[0067] Step 3: Deep fusion of spatio-temporal features extracted from video clips using deep belief network;

[0068] Step 4: Use the average pooling method to obtain the global features of the video sequence;

[0069] Step 5: Use the support vector machine to realize the expression recognition of the video sequence, and output the recognition result.

[0070] One, the realization of each step of this system block diagram, concrete expression is as follows in conjunction with embodiment:

[0071] (1) Preprocessing of video sequences

[0072] From the RML video sequence expression databa...

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 video sequence expression recognition method based on mixed deep learning. The method comprises the following steps: (1) preprocessing the video sequence; (2) extracting spatio-temporal features of video clips by using spatio-temporal convolution neural network; (3) using a deep belief network to realize deep fusion of spatio-temporal features extracted from video clips;(4) obtaining global features of video sequences by using average pooling method; (5) using a support vector machine (SVM) to realize the facial expression recognition of video sequence, and outputting the recognition result. The method can effectively improve the performance of the expression recognition of the video sequence, and can be used in the fields of intelligent human-computer interaction, intelligent video monitoring and the like.

Description

technical field [0001] The invention relates to the fields of image processing, pattern recognition and artificial intelligence, in particular to a video sequence expression recognition method based on hybrid deep learning. Background technique [0002] Facial expression recognition in video sequences refers to the automatic identification of facial expression states in video sequences by computer, so as to determine the psychological emotions of the recognized objects, such as anger, happiness, sadness, fear, etc. This research has important application value in the fields of intelligent human-computer interaction and intelligent video surveillance. [0003] A basic video sequence expression recognition system mainly has three steps: video preprocessing, expression feature extraction and expression classification. Video preprocessing is mainly to detect and extract faces from sequence images in video. Expression feature extraction refers to extracting feature parameters t...

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): G06K9/00
CPCG06V40/175G06V40/161G06V20/49
Inventor 张石清赵小明潘仙张
Owner TAIZHOU 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