Analysis of Facial Sentiments: A deep-learning Way

Abstract

Human facial expressions are an integral and straightforward means of displaying sentiments. Automatic analysis of these unspoken sentiments has been an interesting and challenging task in the domain of computer vision with its applications ranging across multiple domains including psychology, product marketing, process automation etc. This task has been a difficult one as humans differ greatly in the manner of expressing their sentiments through expressions. Machine learning, specifically deep learning has been instrumental in making breakthrough progress in many fields of research including computer vision. This research paper introduces a convolutional neural network (CNN) implemented architecture that tackles this problem of facial sentiment analysis. For training and testing purposes, the FER-2013 public dataset is utilized. This task has been undertaken in a series of steps namely, preprocessing of the data followed feature extraction and finally classification by our trained model network. The results of our experiment have been a very encouraging 57% and are an improvement in the domain of automated analyzing of facial sentiments.