An efficient face recognition system based on embedded DCT pyramid

Abstract

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 waveletbased 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 1 .

Compression Based Face Recognition Using DWT and SVM

“…The algorithm is tested on datasets like ORL, YALE, Extended YALEB and PIE. Randa Atta and Ghanbar [12] Proposed An Efficient Face…”

Best Basis Selection Method Using Learning Weights for Face Recognition

“…However, we easily find recent studies using these outline facial images instead of pure faces [ 28 , 29 ]. This is because face images of typical benchmark face databases (FERET, CMU PIE datasets) include facial outlines [ 30 , 31 ].…”

“…This is because face images of typical benchmark face databases (FERET, CMU PIE datasets) include facial outlines [ 30 , 31 ]. Additionally, most researchers are busy trying to propose new high performance algorithms such as a pyramid decomposition [ 28 ]. Thus, we should be reminded of the important of these pure faces.…”

Non-uniform patch based face recognition via 2D-DWT

“…These methods show better performance when confronted with some problem such as illumination and the singular in linear discriminant analysis (LDA), to some extent, which draw the attention upon an image from global to local. By combining patch technique with some other methods, many effective face recognition methods have been proposed recently in the literature [16][17][18][19][20][21][22][23][24]. From the above papers, it is not difficult to find that there are two basic kinds of patches: one is overlapped patches as in [16,17]; and another is non-overlapped patches as in [22,23].…”