FACIAL EMOTION RECOGNITION USING CONVOLUTIONAL NEURAL NETWORK
Abstract
vioft2nntf2t|tblJournal|Abstract_paper|0xf4ffb1f22b0000008f1f060001000800
Facial expressions play a significant role in social communication since they convey a lot of information about people, such as moods, emotions, and other things. Many researchers gained an optimal accuracy in most of the popular facial recognition datasets: CK+, JAFFE, IEV, but in FER2013 the best model accuracy is about 74%. This article purpose deep learning-based models to mitigate this issue. Three models based on AlexNet, VGG19, and ResNet50 are used to train with the dataset, and the very best model among them is further analyzed. The best model is trained using various optimizers and evaluated based on its training and testing accuracy, confusion matrix, ROC Curve. The finest model gained an accuracy of 91.89504% which is better than past state of art models by at least 17% accuracy.

Authors
Milan Tripathi
Tribhuvan University, Nepal

Keywords
Facial Expression, Confusion Matrix, Emotion, Optimizer, Receiver Operating Characteristic Curve
Yearly Full Views
JanuaryFebruaryMarchAprilMayJuneJulyAugustSeptemberOctoberNovemberDecember
000001000000
Published By :
ICTACT
Published In :
ICTACT Journal on Image and Video Processing
( Volume: 12 , Issue: 1 , Pages: 2531-2536 )
Date of Publication :
August 2021
Page Views :
213
Full Text Views :
2

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.