Spectral Face Recognition Using Orthogonal Subspace Bases

摘要

We present an efficient method for facial recognition using hyperspectral imaging and orthogonal subspaces. Projectingthe data into orthogonal subspaces has the advantage of compactness and reduction of redundancy. We focus on twoapproaches: Principal Component Analysis and Orthogonal Subspace Projection. Our work is separated in three stages.First, we designed an experimental setup that allowed us to create a hyperspectral image database of 17 subjects underdifferent facial expressions and viewing angles. Second, we investigated approaches to employ spectral information forthe generation of fused grayscale images. Third, we designed and tested a recognition system based on the methodsdescribed above. The experimental results show that spectral fusion leads to improvement of recognition accuracy whencompared to regular imaging. The work expands on previous band extraction research and has the distinct advantage ofbeing one of the first that combines spatial information (i.e. face characteristics) with spectral information. In addition,the techniques are general enough to accommodate differences in skin spectra.