The most commonly used vision-based coding system is the Facial Action Coding System (FACS) proposed by Ekman and Friesen [5] for The Facial Action Coding System: A technique for measuring facial motion, FACS enables the analysis of facial expression through standardized coding of changes in facial motion in terms of atomic facial actions called Action Units (AUs). Facial activity tracking and recognition are characterized by three levels, in the first lower level facial feature points around each component of the face are captured. The second intermediate level, facial action units defined using the Facial Action Coding System (FACS), represent the contribution of a specific set of facial muscles. Finally, at the highest level, six prototypical facial expressions represent the global movement of facial muscles and are commonly used to describe human emotional states. Lyons et al. [6] Facial attribute classification using a 2-D Gabor wavelet representation and discriminant analysis used a series of multiscale, multiorientation Gabor filters to first transform the images. The Coef Gabor...