JOURNAL OF MULTIMEDIA (JMM)
ISSN : 1796-2048
Volume : 1    Issue : 6    Date : September 2006

Analysis of Facial Dynamics Using a Tensor Framework
Lisa Gralewski, Neill Campbell, Edward Morrison and Ian Penton-Voak
Page(s): 10-21
Full Text:
PDF (809 KB)


Abstract
Research has shown that the dynamics of facial motion are important in the perception of gender,
identity, and emotion. In this paper we show that it is possible to use a multi-linear tensor
framework to extract facial motion signatures and to cluster these signatures by gender or by
emotion. Here, we consider only the dynamics of internal features of the face (e.g. eyebrows, eyelids
and mouth) so as to remove structural and shape cues to identity and gender. Such structural
gender biases include jaw width and forehead shape and their removal ensures dynamic cues
alone are being used. Additionally, we demonstrate the generative capabilities of using a tensor
framework, by reliably synthesising new motion signatures; and find results comparable to human
psychology experiments performed on the same facial motion data.

Index Terms
Tensor Framework, HOSVD, Facial Motion Analysis, Motion Signatures