A Deep Learning Facial Emotion Classification system: a VGGNet-19 based approach

after studying the pretrained VGGNet 19 model, we figured out that this model contains a large number of parameters that tend likely towards overfitting, which blocks the face expression recognition performance. This indicates that there is always some room for improvement. In this manuscript, we pr...

Full description

Saved in:
Bibliographic Details
Published in2020 20th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering (STA) pp. 271 - 276
Main Authors Abbassi, Nessrine, Helaly, Rabie, Hajjaji, Mohamed Ali, Mtibaa, Abdellatif
Format Conference Proceeding
LanguageEnglish
Published IEEE 20.12.2020
Subjects
CK
Convolution
convolution layer
Degradation
Dropout
Emotion recognition
Face recognition
Facial Expression Recognition
FER 2013
Image classification
Task analysis
Training
VGGNet-19
Online AccessGet full text

Cover

More Information
Summary:after studying the pretrained VGGNet 19 model, we figured out that this model contains a large number of parameters that tend likely towards overfitting, which blocks the face expression recognition performance. This indicates that there is always some room for improvement. In this manuscript, we propose a new approach based on the VGGNet-19 network, in which we use several convolution layers with small filters and a dropout strategy. In the adopted model, the addition of convolution layers is recommended in order to give more precision to image classification. The experiment results suggest that the proposed model give promising results.
ISSN:2573-539X
DOI:10.1109/STA50679.2020.9329355