Localized versus Locality Preserving Representation Methods in Face Recognition Tasks

摘要: Four different localized representation methods and two manifold learning procedures are compared in terms of recognition accuracy for several face processing tasks. The techniques under investigation are: a) Non-negative Matrix Factorization (NMF); b) Local (LNMF); c) Independent Components Analysis (ICA); d) NMF with sparse constraints (NMFsc); e) Locality Preserving Projections (Laplacianfaces); f) Orthogonal Projection Reduction by Affinity (OPRA). A systematic comparative analysis is conducted distance metric used, number selected features, sources variability on AR, Yale, Olivetti databases. Results indicate that the relative performance ranking highly task dependent, varies significantly upon used.