Classifying facial actions

TLDR

The facial action coding system (FACS) is an objective method for quantifying facial movement in terms of component actions. This paper explores and compares techniques for automatically recognizing facial actions in sequences of images. These techniques include analysis of facial motion via optical flow, holistic spatial analysis such as PCA, ICA, local feature analysis, and LDA, and methods based on local filter outputs like Gabor wavelet representations and local principal components, with performance compared to naive and expert human subjects. Best performances were achieved using the Gabor wavelet representation and the independent component representation, each reaching 96 % accuracy for classifying 12 facial actions of the upper and lower face, confirming the importance of local filters, high spatial frequencies, and statistical independence.

Abstract

The facial action coding system (FAGS) is an objective method for quantifying facial movement in terms of component actions. This paper explores and compares techniques for automatically recognizing facial actions in sequences of images. These techniques include: analysis of facial motion through estimation of optical flow; holistic spatial analysis, such as principal component analysis, independent component analysis, local feature analysis, and linear discriminant analysis; and methods based on the outputs of local filters, such as Gabor wavelet representations and local principal components. Performance of these systems is compared to naive and expert human subjects. Best performances were obtained using the Gabor wavelet representation and the independent component representation, both of which achieved 96 percent accuracy for classifying 12 facial actions of the upper and lower face. The results provide converging evidence for the importance of using local filters, high spatial frequencies, and statistical independence for classifying facial actions.