A Review on Facial Expression Recognition System using Deep Learning

Abstract

Human emotions are spontaneous and conscious mental states of feeling that are accompanied by physiological changes in the face muscles implying face expression. Some important emotions are happy, sad, anger, disgust, fear, surprise, neutral, etc. In non-verbal communication, facial expressions play a very important role because of the inner feelings of a person that reflect on faces. A lot of studies have been carried out for the computer modeling of human emotion. However, it's far behind the human vision system. In the area of computer vision, academic research in deep learning, specifically research into convolutional neural networks, received a lot of attention with the fast growth of computer hardware & the arrival of the Big Data era. Many researches & studies on emotion recognition & deep learning methods are carried out to identify emotions. This article presents a survey of Face Expression Recognition (FER) methods, including 3 key phases as pre-processing, extraction of features & classification. This survey discusses the many kinds of FER methods followed by categories & methods of emotional recognition. It also gives a brief overview of the deep learning approaches used in the FER classification system for facial emotion.