Person independent facial expression recognition using 3D facial feature positions

Abstract

Facial expressions contain a lot of information about the feelings of a human. They play an important role in human-computer interaction. In this paper, we propose a person independent facial expression recognition algorithm based on 3-Dimensional (3D) geometrical facial feature positions to classify the six basic expressions of the face: Anger, disgust, fear, happiness, sadness and surprise. The algorithm is tested on BU-3DFE database and provides encouraging recognition rates. © 2013 Springer-Verlag London.