In this paper, we use deep learning to make an emotion recognition convolution neural network by customizing the EfficientNet model pretrained on the ImageNet dataset. We used the FER-2013 dataset available in the Wolfram repository. Seven classes of emotions are considered in the dataset: happy, sad, angry, surprise, disgust, fear, and neutral. We try out different methods to tackle class imbalance.
Diya Elizabeth1, Siria Sadeddin2
Indian Institute of Science Education and Research, Thiruvananthapuram, India1, Universidad Nacional de Colombia, Colombia2
Undersampling, Weighted Sampling, Focal Loss
| January | February | March | April | May | June | July | August | September | October | November | December |
| 2 | 6 | 12 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| Published By :
ICTACT
Published In :
ICTACT Journal on Data Science and Machine Learning
( Volume: 5 , Issue: 1 , Pages: 547 - 549 )
Date of Publication :
December 2023
Page Views :
132
Full Text Views :
20
|