Improving Face Recognition Performance Using RBPCA MaxLike and Information Fusion
Denis H. P. Salvadeo, Nelson D. A. Mascarenhas, Jander Moreira, Alexandre L. M. Levada, Débora Corrêa · Computing in Science & Engineering · 2010
Face recognition is typically an ill-posed problem because of the limited number of available samples. As experimental results show, combining multiclassifier fusion with the RBPCA MaxLike approach, which couples covariance matrix regularization and block-based principal component analysis (BPCA), can provide an effective framework for face recognition that alleviates the small sample size problem.