Abstract
Facial expression is the external expression of inner emotion, and is the main medium for analyzing emotion-guided sentiment, which has great research value. And for the problems of low accuracy and slow convergence of current models for face expression recognition. This paper proposed the ReSE face expression recognition model based on the residual network through the study of face expression recognition. The ReSE model is mainly constructed by ResNet18 and RE module, while using PReLU function instead of ReLU function, introducing Dropout function, and finally using island loss classification function. Through experimental validation, the average accuracy of the ReSE model for face expression recognition on the Fer2013 dataset is 1.33 percentage points higher than that of the VGG16 model; the average accuracy of the ReSE model for face expression recognition on the CK+ dataset is 1.36 percentage points higher than that of the ResNet18 model. Follow-up research needs to reduce the number of model parameters and further optimize the network structure for improving the accuracy of facial expression recognition.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
