Comparative analysis of emotion recognition methods

Abstract

Recent technological advances have enabled human users to interact with computers in ways previously unimaginable. The aim our thesis is to find out a system where computer can communicate with human more efficiently and more friendly. For that purpose we do studies various possible ways for a computer to communicant with human with limited recourses. In this paper we are trying to describe various algorithms and processes that have been studied all around the world. We also discuss the difficult issues of obtaining reliable affective data, obtaining ground truth for emotion recognition, and the use of unlabeled data.