50 likes | 249 Views
Eigenface and Fisher Face. PCA (Eigenface) approach maps features to principle subspaces that contains most energy. Fisher linear discriminating (FLD, Fisherface) approach maps the feature to subspaces that most separate the two classes. Comparing Eigen-face and Fisher Face.
E N D
PCA (Eigenface) approach maps features to principle subspaces that contains most energy. Fisher linear discriminating (FLD, Fisherface) approach maps the feature to subspaces that most separate the two classes. Comparing Eigen-face and Fisher Face Belhumeur, et al. IEEE Trans PAMI, July 1997, pp 771-720
Fisher Linear Discriminating Solution Equivalent, wopt can be found by maximizing wTSBw subject to wTSWw = 1. This gives a LaGrange Multiplier:
Technical Challenges • Within cluster scattering matrix SW is often singular in face recognition problem since the # of training faces is often smaller than the # of pixels in a face image.