Steerable Pyramids Feature Based Classification Using Fisher Linear Discriminant for Face Recognition

Abstract

In this paper, an efficient local appearance feature extraction method based the multiresolution Steerable Pyramids (SP) transform is proposed in order to further enhance the performance of the well known Fisher Linear Discriminant (FLD) method when applied to face recognition. Each face is described by a subset of band filtered images containing block-based SP coefficients. These coefficients characterize the face texture and a set of simple statistical measures allows us to form compact and meaningful feature vectors. The proposed method is compared with some related feature extraction methods such as Principal component analysis (PCA), as well as Linear Discriminant Analysis, and Fisher Linear Discriminant (FLD), Independent Component Analysis and ICA. Experimental results on ORL, YALE and FERET face databases convince us that the proposed method provides a better representation of the class information and obtains much higher recognition accuracies