Objects can be described by different cues. For example, objects can be described by geometrical primitives like boxes, spheres, cones, and cylinders. Describing and representing objects based on their appearance is a widely studied approach in the literature (Bartlett, Movellan, & Sejnowski, 2002; Belhumeur, Hespanha, & Kriegman, 1997; Dorko & Schmid, 2005; Lowe, 2004; Mikolajczyk, Leibe, & Schiele, 2005; Serre, Wolf, Bileschi, Riesenhuber, & Poggio, 2007; Shechtman & Irani, 2007; Turk & Pentland, 1991; H. Zhang, Gao, Chen, & Zhao, 2006). The general idea of appearance-based object recognition is to extract useful and robust information from only the appearance of the object-of-interest that is usually captured by different two-dimensional views. Appearance-based methods can be sub-divided into two main classes: local and global approaches.