Review on Detecting Facial Emotions Using Deep Learning for Mental Health Applications

Facial Emotion Recognition (FER) maps diverse facial emotions to a wide variety of emotional states. Different facial emotions and expressions play a significant role in the communication of emotions via non-verbal channels, making them an extremely efficient technique for expressing humans’ internal thoughts to society. Facial emotions have been applied in a wide range of applications, such as healthcare, cyber-security, human-machine interfaces, and more. Over the past decades, FER has become a challenging research problem addressed by several researchers using different Machine Learning (ML) and Deep Learning (DL) techniques. However, in psychological patients, their emotions are often associated with various mental health issues. To address this, the paper presents a review of several DL techniques and infers that ResNet-50 is the best classifier for predicting mental health via facial emotions/expressions, achieving an efficient accuracy of 95.39% with minimal time complexity.