On the dissimilarity of orthogonal least squares and orthogonal matching pursuit compressive sensing reconstruction

Abstract

Compressive sensing is a recent technique in the field of signal processing that aims to recover signals or images from half samples that were used by Shannon Nyquist theorem of reconstruction. For recovery using compressed sensing, two well known greedy algorithms are used-Orthogonal matching pursuit and orthogonal least squares. Generally these two algorithms are taken as same by the researchers which is not true. There is a remarkable difference between the two algorithms that is pointed out in this paper with the simulation results. The previous article clarifying the difference between these two algorithms are emphasized on theoretical difference and does not show any reconstruction simulation difference with these two algorithms and reason to preference over basis pursuit method The key aim of this paper is to remove the confusion between the two algorithms on the basis of theory and reconstruction time taken with the output PSNR. © Springer International Publishing Switzerland 2014.