Facial expression recognition method, device and equipment based on ResNeXt network and storage medium
A facial expression recognition and facial expression technology, applied in the field of image processing, can solve the problems of low recognition accuracy, long training time, and high computational cost, and achieve the effect of improving the recognition rate and reducing the training time and sum.
Active Publication Date: 2021-06-22
CHINA UNIV OF GEOSCIENCES (WUHAN)
View PDF8 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004]
The present invention provides a facial expression recognition method, device, equipment and storage medium based on the ResNeXt network, aiming to solve the technical problems of high computational cost, long training time and low recognition accuracy of traditional complex neural networks
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
[0055] In order to make the purpose, technical solution and advantages of the present invention clearer, the embodiments of the present invention will be further described below in conjunction with the accompanying drawings.
[0056]A specific embodiment of the present invention is a method for recognizing facial expressions based on the ResNeXt network. In this embodiment, the ResNeXt network is used as the BackBone (backbone network), and the ResNeXt network is optimized and improved, and the residual mapping learning is used to replace the identity mapping learning, stacking The basic unit with the same topology and high modularity can effectively avoid performance degradation problems and reduce network complexity when training deep neural networks, so that the training of deep networks can quickly tend to converge, providing for the diversity of expression samples and High dimensionality provides sufficient parameter space. At the same time, for expression classification ...
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 invention provides a facial expression recognition method, device and equipment based on a ResNeXt network, and a storage medium. The method comprises the following steps: selecting a training data set and a to-be-recognized data set from a facial expression image; constructing a facial expression recognition model based on the improved ResNeXt network; selecting a part of facial expression images from the training data set, inputting the facial expression images into a facial expression recognition model, and performing iterative training to obtain a trained facial expression recognition model; and selecting a part of facial expression images from the to-be-recognized data set, inputting the facial expression images into the trained facial expression recognition model, and performing facial expression recognition to obtain a facial expression classification result. According to the method, the facial expressions can be accurately identified and classified, and the trained ResNeXt network model is used for real-time identification under a complex real condition, so that the calculation time can be saved, and the quick identification of the facial expressions is realized.
Description
technical field [0001] The present invention relates to the technical field of image processing, in particular to a ResNeXt network-based facial expression recognition method, device, equipment and storage medium. Background technique [0002] In the way of communication between people, in addition to direct language communication, facial expression is a very important transmission medium for conveying personal thoughts and perceiving other people's behavior information. Although the face only occupies a very small part of the overall structure of human beings, the rich changes in facial features can show the extremely rich inner world of human beings, which can be called the display screen of human psychology. Therefore, expression is the most direct transmission medium of human inner world, and occupies the most important position in human communication. To understand human emotions, we need to start from facial expression recognition. Facial expressions are the most dire...
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 Applications(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/171G06V40/174G06V10/446G06N3/048G06N3/045G06F18/285G06F18/2415
Inventor 吴中天刘峰李志华黄书贤胡乐
Owner CHINA UNIV OF GEOSCIENCES (WUHAN)