Dynamic vs. Static Recognition of Facial Expressions

Abstract. In this paper, we address the dynamic recognition of basic fa-cial 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 sev-eral classification schemes. With the proposed scheme, we developed an application for social robotics, in which an AIBO is mirroring the facial expression recognized.