ADAPTIVE WAVELETS FOR IMAGE REPRESENTATION AND CLASSIFICATION (WedAmOR11)

Author(s) : Gemma Piella (GET-ENST, France) Marine Campedel (GET-ENST, France) Béatrice Pesquet-Popescu (GET-ENST, France)

Abstract : In this paper we describe and analyze a new scheme for performing feature extraction on large image datasets. The work is motivated primarily by the need to classify quickly and efficiently large multispectral satellite images. We propose a multiresolution approach based on a special class of adaptive wavelets which allows the extraction of salient features without loosing accuracy.

Menu