Skip to Main Content
In this paper, an efficient feature selection method based on a combination of DCT pyramid for image decomposition and the concept of the set partitioning in hierarchal trees (SPIHT) for structuring of information for face recognition is presented. In the proposed method, the DCT pyramid decomposes each face image into an approximation subband and a set of reversed L-shape blocks containing the high frequency coefficients. The generalized parent-child relationships of SPIHT algorithm are then established among the DCT pyramids. This leads to efficient selection of the most important coefficients among the layers of the DCT pyramid. Experimental results on the standard ORL and FERET databases show that the proposed method achieves more accurate face recognition than the wavelet-based SPIHT feature selection. Moreover, it outperforms the other well-known methods such as the Eigenfaces and the block-based DCT with the zigzag scanning structure in terms of both accuracy and memory requirement.