A Novel Spatially Confined Non-Negative Matrix Factorization for Face R ecognition
Hf Neo, Bj Teoh, Cl Ngo, Jalan Ayer K eroh Lama, Malay Sia · Siti Hasmah Digital Library-MMU Institutiona Repository (Multimedia University) · 2005
In this paper, a novel method for facial representation called Spatially Confined Non-Negative Matrix Factorization (SFNMF) is presented. SFNMF aims to extract more spatially confined, parts-based representation from the NMF based representation by merely removing non-prominent region, and focalize on the salient feature. SFNMF derived a significant set of basis which allows a non-subtractive representation of images and these bases manifest localized features. Experimental results are presented to compare SFNMF with NMF and Local NMF. Advantageous of SFNMF is demonstrated when SFNMF achieves highest verification rate among the other.