4D facial expression recognition
Tianhong Fang, Xi Zhao, Shishir K. Shah, Ioannis A. Kakadiaris · 2011
In this paper, we focus on discrete expression classification using dynamic 3D sequences (4D data) recording the facial movements. A robust approach for registering 4D data is proposed and a variant of local binary patterns on three orthogonal planes is used for feature extraction. We present a fully automatic facial expression recognition pipeline. The system was evaluated on the publicly available facial expression database BU-4DFE and promising results were obtained.