A FAST WAVELET-BASED KARHUNEN-LOEVE TRANSFORM

The paper describes the role of the standard wavelet decomposition in computing a fast Karhunen-Loeve transform. The standard wavelet decomp osition (which we show is different from the conventional wavelet tran sform) leads to a highly sparse and simply structured transformed vers ion of the correlation matrix which can be easily subsetted (with litt le loss of Frobenius norm). The eigenstructure of this smaller matrix can be efficiently computed using standard algorithms such as QL. Fina lly, we provide an example of the use of the efficient transform by cl assifying a 219-channel AVIRIS image with respect to its eigensystem. (C) 1998 Pattern Recognition Society. Published by Elsevier Science Lt d. All rights reserved.