SAR image feature extraction and classification with fractal-based description

Abstract

In the field of synthetic aperture radar (SAR) image analysis, an effective feature extraction method based on a fractal Brownian increment random field (FBRIR) is introduced, and an effective classification method with a neuron network based on adaptive resonance theory (ART) is designed accordingly. At last the validity of this systematic approach is tested and compared using real data of Ku band SAR images.