Optimization of machine learning algorithm of emotion recognition in terms of human facial expressions

Abstract

This work is devoted to the optimization of the recognition method of seven basic emotions (joy, sadness, fear, anger, surprise, disgust and neutral) in terms of the expressions of the human face. The existing approaches of the emotion recognition systems construction was analyzed based on human facial expressions, and focused on the advantages of using scheems based on neural networks. We proposed a method of constructing an emotion recognition system based on a neural network, which includes an optimized algorithm for generating training and test samples, as well as determining the rational number of layers of the neural network.