Emotion Recognition using Autoencoders: A Systematic Review

Abstract

During recent decades, facial expression recognition is a hot area of research in deep learning and computer vision. However, numerous research has been done on emotion recognition through facial expression using deep neural networks and achieved remarkable results on image datasets. Moreover, convolutional neural networks (CNN) often require a large number of layers when extracting useful information from facial images, thus increasing the network complexity and training time. For overcoming the challenges in CNN, researchers have been employing autoencoders to recognize facial emotions. This paper reviews all available work on autoencoders using facial expression recognition, and variations in autoencoders. For this analysis, a literature review paper has been collected from IEEE, Scopus, and Web of Science databases. Furthermore, publicly available facial expression recognition benchmark datasets are discussed. In addition, this paper discusses how unsupervised autoencoder has been applied in classification problems. Furthermore, this comprehensive review will be helpful for young researchers in FER and provide an overview of autoencoder in facial emotion recognition using facial expressions.