University of Houston

Facial expression analysis has interested many researchers in the past decade due to its potential applications in various fields such as human-computer interaction, psychological studies and facial animation. There has been extensive research using 2D images or video sequences, most of which however, assumes well-lit environment and little rigid head motion. Recently, more attention has been given to 3D sensors to overcome the insufficiencies of 2D data, as promise was shown in their successful applications in face recognition.

This thesis focuses on discrete expression classification using 3D data from the human face. First, an expression recognition framework using static 3D images is presented. It is based on an improved version of the deformable model approach and is highly extensible. In the second part of this thesis, a systematic pipeline that operates on dynamic 3D sequences (4D datasets or 3D videos) is proposed and alternative modules are investigated as a comparative study. We evaluated both systems on two publicly available facial expression databases and obtained promising results.