Facial expression recognition method and system
A recognition method and facial expression technology, applied in the field of computer vision, can solve the problem of low accuracy of facial expression recognition, and achieve the effect of improving accuracy
Active Publication Date: 2022-07-12
UNIVERSITY OF CHINESE ACADEMY OF SCIENCES
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In view of the above problems, the object of the present invention is to provide a facial expression recognition method and system, which can effectively solve the problem of low accuracy of facial expression recognition due to different lighting, posture differences, and occlusion diversification in uncontrolled scenes. question
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0030] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are some, but not all, embodiments of the present invention. Based on the described embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art fall within the protection scope of the present invention.
[0031] The present invention can identify 7 types of basic expressions and 1 neutral expression on human faces. First, extract each frame of image from the video, and perform face detection and localization on each frame of image. Next, the cropped face image is input into the facial expression recognition network constructed based on spatial attention module and residu...
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
Login to View More Abstract
The present invention relates to a facial expression recognition method and system, comprising: collecting face video, detecting whether there is a face area for each frame of video, if yes, then entering the next step, if not, skipping and entering the processing of the next frame of image; A preset number of facial feature points are detected in the face area; based on the coordinate positions of the facial feature points, the facial area image is calculated and cropped; the cropped facial area image is scaled and input into the trained lightweight space The facial expression recognition network model embedded in the attention module obtains the predicted probability value of each emotion category, and the category with the highest probability is used as the expression recognition result and output. The invention can recognize 7 basic expressions and 1 neutral expression of human face, can improve the recognition accuracy of facial expressions in uncontrolled environment on the basis of embedding a small number of attention modules, and can be widely used in the field of computer vision technology.
Description
technical field [0001] The invention relates to the technical field of computer vision, in particular to a facial expression recognition method and system based on the embedding of lightweight spatial attention modules. Background technique [0002] Emotions, as a kind of important information transmitted by human beings in the process of communication, can help us obtain auxiliary information other than language content, so as to conduct more adequate and effective communication. Facial expression recognition, as one of the widely used technologies in sentiment analysis in recent years, usually adopts the steps of collecting facial images or video sequences, performing face detection (or tracking and positioning), feature extraction in sequence, and finally completing expression prediction. At present, the facial expression images collected in the laboratory controllable scene can achieve a relatively good recognition effect. For example, most models can achieve an accuracy...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06V40/16G06V10/26G06V10/32G06V10/774G06V10/82G06K9/62G06N3/04
CPCG06V40/174G06V40/172G06V40/168G06V10/32G06V10/267G06N3/045G06F18/214
Inventor 薛健王聪吕科
Owner UNIVERSITY OF CHINESE ACADEMY OF SCIENCES