Face-emotion recognition method, device, terminal device and storage medium

A technology of facial emotion and recognition method, which is applied in the computer field, can solve the problems that the accuracy of facial expression recognition is not particularly high, it is difficult to accurately divide expressions, and the computer cannot accurately locate feature points, so as to ensure stability and Effects of recognition rate, dimensionality reduction, and noise elimination

Inactive Publication Date: 2019-01-04
XIAMEN UNIV OF TECH
View PDF9 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in terms of emotion detection problems, since the computer cannot accurately locate the specific orientation of the feature points, even if they have the same expression, different people have different facial expressions
It is difficult for a computer to divide each expression precisely
Therefore, the accuracy of computer recognition of facial expressions is not particularly high

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
  • Face-emotion recognition method, device, terminal device and storage medium
  • Face-emotion recognition method, device, terminal device and storage medium
  • Face-emotion recognition method, device, terminal device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0041] see Figure 1 to Figure 3 , figure 1 It is a schematic flow chart of a facial expression recognition method provided in the first embodiment of the present invention, figure 2 A schematic diagram of the results of the convolutional neural network model provided by the embodiment of the present invention, image 3 A schematic structural diagram of the VGG algorithm provided by the embodiment of the present invention. The invention provides a facial expression recognition method comprising:

[0042] S10. Obtain the current data frame in the video stream.

[0043] In this embodiment, the video stream is composed of consecutive pictures, and each picture is a frame. Simply put, the number of frames is the number of frames of pictures transmitted in 1 second, and it can also be It is understood that the graphics processor can refresh several times per second, usually expressed in fps (Frames Per Second). Each frame is a still image, and displaying frames in rapid succe...

no. 2 example ；

[0077] see Figure 4 , Figure 4 It is a schematic structural diagram of a facial expression recognition device provided by the second embodiment of the present invention. The present invention provides a human face emotion recognition device, specifically comprising:

[0078] An acquisition module 100, configured to acquire the current data frame in the video stream;

[0079] Capture module 200, for capturing the human face from the current data frame, and extracting the feature information of the human face;

[0080] The identification module 300 is configured to pass the feature information through the pre-trained expression classification model to identify the expression classification of the face according to the extracted feature information of the human face;

[0081] The sending module 400 is configured to send the expression classification result to the associated robot, so that the associated robot can feedback the result of classification of human facial expressi...

no. 3 example

[0095] The third embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processing, when the processor executes the computer program, the present invention is implemented. The facial expression recognition method described in the first embodiment above.

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 face emotion recognition method, a device, a terminal device and a storage medium. The method comprises the following steps: obtaining a current data frame in a video stream,capturing a face from the current data frame, and extracting the characteristic information of the face; according to the extracted facial feature information, the feature information is used to classify the facial expression through the pre-trained expression classification model. The result of facial expression classification is sent to the associative robot so that the associative robot can feedback the result of facial expression classification in the form of speech. The invention precisely locates the specific orientation of the feature points, and then recognizes different expression classification results of the face.

Description

technical field [0001] The present invention relates to the field of computers, in particular to a method, device, terminal equipment and storage medium for facial emotion recognition. Background technique [0002] Humans rely on emotion to convey the response of others, and when the wording and the expressed message are inconsistent, the expressed message is more accurate. Therefore, expression is an important way for human emotional communication, and human emotions are mainly conveyed through facial expressions. With the advancement in the field of artificial intelligence, humans started using computers to determine human emotions. In the prior art, with the development of deep learning in the field of computer vision, computers are used to solve problems such as object detection, motion recognition, anomaly detection, video surveillance, and to solve emotion detection. However, in terms of emotion detection, since the computer cannot accurately locate the specific loca...

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 & AuthorityApplications(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/174G06V40/161G06V40/168G06F18/214
Inventor庄礼鸿郑旺
OwnerXIAMEN UNIV OF TECH