An Automatic Multilevel Facial Expression Recognition System

Abstract

Facial expression is one of the most natural way of human beings tocommunicate his-her internal feeling, to stress his-her words, to agree or disagreewith the interlocutor, to regulate interaction with the environment and nearbypeople. This paper challenges the classification experiment run by human beingson the ADFES-BIV database, which is a recently introduced collection of videosexpressing low, middle, and high intensity emotions. The proposed automaticsystem uses the Sparse Representation based Classifier and reaches the topperformance of 80 % by considering the temporal information intrinsically presentin the videos.