View-subspace analysis of multi-view face patterns

Multi-view face detection and recognition has been a challenging problem. The challenge is due to the fact that the distribution of multi-view faces in a feature space is more dispersed and more complicated than that of frontal faces. This paper presents an investigation into several view-subspace representations of multi-view faces: learning by using independent component analysis (ICA), independent subspace analysis (ISA) and topographic independent component analysis (TICA). It is shown that view-specific basis components can be learned from multi-view face examples in an unsupervised way by using ICA, ISA and TICA; whereas the components learned by using principal component analysis reveal little view-related information. The learned results provide sensible basis for constructing view-subspaces for multi-view faces. Comparative experiments demonstrate distinctive properties of ICA, ISA and TICA results, and the suitability of the results as representations of multi-view faces.