Quintano, C, Cuesta, E (2010). Improving satellite image classification by using fractional type convolution filtering. INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 12(4), 298-301.
This letter shows how conventional methods for satellite image classification can be improved by applying some filtering algorithms as a pre-classifying step. We will introduce a filtering scheme based on convolution equations of fractional type. The use of this kind of filter as a pre-classification step will be illustrated by classifying MODerate-resolution Imaging Spectroradiometer (MODIS) data to map burned areas in Mediterranean countries. The methodology we propose improved the estimations obtained by merely classifying the post-fire images (i.e. without filtering) in the study areas considered. (C) 2010 Elsevier B.V. All rights reserved.