Face recognition using block-based DCT and weighted generalized KFD

Abstract

An improved feature extraction for face recognition is presented in this paper. In the proposed technique, the input face image is divided into blocks and two-dimensional Discrete Cosine Transform (DCT) approach is applied to each block. Then the low frequencies of all two-dimensional DCT coefficients from each block are extracted and combined to form a feature vector. Thereafter, weighted generalized kernel Fisher discriminant is performed on these vectors. Experimental results on the ORL face database demonstrate the effectiveness of the proposed method. © 2012 Springer-Verlag GmbH.