A James-Stein Estimator based Generalized OMP Algorithm for Robust Signal Recovery using Sparse Representation

Abstract

In this paper, we introduce a novel algorithm named JS-gOMP, which enhances the generalized Orthogonal Matching Pursuit (gOMP) algorithm for improved noise robustness in sparse signal processing. The JS-gOMP algorithm uniquely incorporates the James-Stein estimator, optimizing the trade-off between signal recovery and noise suppression. This modification addresses the challenges posed by noise in the dictionary, a common issue in sparse representation scenarios. Comparative analyses demonstrate that JS-gOMP outperforms traditional gOMP, especially in noisy environments, offering a more effective solution for signal and image processing applications where noise presence is significant.