A Comprehensive Investigation on Emotional Detection in Deep Learning

Abstract

Emotion recognition is a substantial problem in the field of Big Data. In a wide range of applications, reliable categorization, analysis, and interpretation of emotional content is greatly desired. In this paper, we look at how Deep Learning models perform on an emotion perception test. Facial Expression Recognition (FER) plays an important role in machine learning tasks. Deep Learning models do well in FER tasks, but they lack explanation for their conclusions. Based on the notion that facial expression is a mixture of facial muscle movements, we discover a link between Facial Action Coding Units (AUs) and Emotion label in the CK+ Dataset. In this study, we offer a model that uses AUs to explain the classification outcomes of a Convolutional Neural Network (CNN) model. The CNN model is trained using the CK+ Dataset and identifies emotions using extracted characteristics. The CNN model's retrieved features and emotion classes are used by the explanation model to classify multiple AUs. Explanation model creates AUs quite effectively with only characteristics and emotion classes acquired from the CNN model, according to our trial. Experimental research was constructed, and several deep learning approaches were tested using publically available datasets. The findings are highly intriguing, highlighting the benefits of each strategy and training style studied.