Facial Action Coding Using Multiple Visual Cues and a Hierarchy of Particle Filters

In this paper we present a framework for tracking nonrigid facial landmarks by combining various visual cues at multiple levels of detail. Using a probabilistic framework consisting of a hierarchy of particle filters, we are able to track individual facial landmarks using multiple visual cues at the local level, as well as tracking results at more coarse level of detail. This allows for the fusion of global and local cues in an efficient and robust manner. Testing is performed by tracking and classifying facial action codes obtained from the Cohn-Kanade AU-Coded Facial Expression Database.