Open AccessA REVIEW ON FACIAL EMOTION RECOGNITION THAT USES MACHINE LEARNING ALGORITHMS
Author(s) -
M. Patel,
Manisha Patel
Publication year - 2021
Publication title -
international journal of engineering applied science and technology
Language(s) - English
Resource type - Journals
ISSN - 2455-2143
DOI - 10.33564/ijeast.2021.v05i11.026
Subject(s) - hyperparameter , convolutional neural network , computer science , artificial intelligence , task (project management) , categorical variable , machine learning , facial recognition system , emotion recognition , face (sociological concept) , pattern recognition (psychology) , facial expression , speech recognition , social science , management , sociology , economics
For a computer, identification of human emotionfrom a still image of the human face is a complex,challenging, and heavily calculative task. Classification ofhuman emotion is done by using a different combination ofconvolutional neural networks (CNN) that task is knownas Facial Emotion Recognition (FER). CNN model isachieved by training and testing on lots of same categoricalimages from the dataset using different hyperparametertuning. The main contribution of this work is to look forvarious CNN architectures, hyperparameter tuning andcompare the performance of those CNN models based onaccuracy and loss while training and testing on FacialEmotion Recognition. This study shall help to provide aguide for the selection of an appropriate CNN model andtuning parameter according to the needs of the applicant.