Machine learning based model to predict Human Emotions using facial features

Abstract

This paper focuses on Emotion Recognition using facial expressions. It aims to detect facial expressions accurately and efficiently. Here, we have used facial expressions as the criteria wherein the lips, eyebrow movement, eyes, etc. are the factors that help us detect various emotions. The purpose of this paper is to serve various fields where emotion recognition will be viable and can be helpful for better outcomes. Spectrums like video gaming, psychology, medical fields, etc. can use Emotion Recognition System in a very positive way. Convolutional Neural Network has developed to help in recognizing emotions through facial expressions and classify them into seven basic categories which are: happy, sad, neutral, surprise, fear, disgust, and angry. So, Convolutional Neural Network is implemented to extract relevant features of the input images and classify them into seven categories. For evaluating the proposed model, Facial Emotion Recognition 2013 dataset is used so that the model achieves the best accuracy rate. Keywords—Convolutional Neural Network (CNN), Facial Emotion Recognition 2013 (FER 2013), Extended Cohn-Kanade (CK+), Japanese Female Facial Expressions (JAFFE), Emotional Facial Action Coding System (EMFACs), Action Units (AUs).