Kernel subclass support vector description for face and human action recognition

In this paper, we present the Kernel Subclass Support Vector Data Description classifier. We focus on face recognition and human action recognition applications, where we argue that sub-classes are formed within the training class. We modify the standard SVDD optimization problem, so that it exploits subclass information in its optimization process. We extend the proposed method to work in feature spaces of arbitrary dimensionality. We evaluate the proposed method in publicly available face recognition and human action recognition datasets. Experimental results have shown that increased performance can be obtained by employing the proposed method.