Wavelet decomposition on high-performance computing systems

Abstract

Wavelet transforms have favorable characteristics over Fourier transform. Due to the recent discovery of a fast sequential algorithm, the past years had a remarkable increase in applying Wavelets. In this paper we present and compare efficient Wavelet decomposition algorithms on parallel architectures. We report and analyze experimental measurements, using NASA remotely sensed images. The results show that the algorithms achieve significant performance gains on current parallel systems and meet applications requirements.