Dynamic vs. Static Recognition of Facial Expressions

In this paper, we address the dynamic recognition of basic facial expressions. We introduce a view- and texture independent schemes that exploits facial action parameters estimated by an appearance-based 3D face tracker. We represent the learned facial actions associated with different facial expressions by time series. Furthermore, we compare this dynamic scheme with a static one and show that the former performs better than the latter. We provide evaluations of performance using several classification schemes. With the proposed scheme, we developed all application for social robotics, in which an AIBO is mirroring the facial expression recognized.