DST Feature Based Locality Preserving Projections for Face Recognition

Locality preserving projection (LPP) is a promising manifold learning approach for dimensionality reduction. However, it often encounters small sample size (3S) problem in face recognition tasks. To overcome this limitation, this paper proposes a discrete sine transform (DST) feature extraction approach and develops a DST-feature based LPP algorithm for face recognition. The proposed method has been tested and evaluated with two public available databases, namely ORL and FERET databases. Comparing with Eigenface, Laplacianface methods, the proposed DST-LPP approach gives superior performance.