Facial Expression Recognition based on a Dual Graph Convolutional Network

The facial expression recognition on non-laboratory database is difficult and challenging. To improve the recognition performance, we propose a dual graph convolutional network, based on which two feature extractors are employed to facial images. The experimental results on RAF-DB and SFEW database...

Full description

Saved in:
Bibliographic Details
Published in2021 CIE International Conference on Radar (Radar) pp. 2412 - 2416
Main Authors Lu, Wanli, Tang, Hui, Chai, Li
Format Conference Proceeding
LanguageEnglish
Published IEEE 15.12.2021
Subjects
Convolutional neural networks
Data models
face expression recognition
Face recognition
Feature extraction
feature fusion
graph convolutional network
image classification
Image recognition
Radar
Online AccessGet full text

Cover

More Information
Summary:The facial expression recognition on non-laboratory database is difficult and challenging. To improve the recognition performance, we propose a dual graph convolutional network, based on which two feature extractors are employed to facial images. The experimental results on RAF-DB and SFEW database show that our proposed method improves the accuracy of facial expression recognition on non-laboratory datasets.
ISSN:2640-7736
DOI:10.1109/Radar53847.2021.10028020