Abstract

The Facial Action Coding System (FACS) \cite{EkmanFriesen78} is an objective method for quantifying facial movement in terms of component actions. This system is widely used in behavioral investigations of emotion, cognitive processes, and social interaction. The coding is presently performed by highly trained human experts. This paper explores and compares techniques for automatically recognizing facial actions in sequences of images. These methods include unsupervised learning techniques for finding basis images such as principal component analysis, independent component analysis and local feature analysis, and supervised learning techniques such as Fisher's linear discriminants. These data-driven bases are compared to Gabor wavelets, in which the basis images are predefined. Best performances were obtained using the Gabor wavelet representation and the independent component representation, both of which achieved 96\% accuracy for classifying twelve facial actions. Once the basis images are learned, the ICA representation takes 90\% less CPU time than the Gabor representation to compute. The results provide evidence for the importance of using local image bases, high spatial frequencies, and statistical independence for classifying facial actions. Measurement of facial behavior at the level of detail of FACS provides information for detection of deceit. Applications to detection of deceit are discussed.