By Topic

Double overrelaxation thresholding methods for sparse signal reconstruction

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Kun Qiu ; ECpE Dept., Iowa State Univ., Ames, IA, USA ; Dogandzic, A.

We propose double overrelaxation (DORE) and automatic double overrelaxation (ADORE) thresholding methods for sparse signal reconstruction. The measurements follow an underdetermined linear model, where the regression-coefficient vector is a sum of an unknown deterministic sparse signal component and a zero-mean white Gaussian component with an unknown variance. We first introduce an expectation-conditional maximization either (ECME) algorithm for estimating the sparse signal and variance of the random signal component and then describe our DORE thresholding scheme. The DORE scheme interleaves two successive overrelaxation steps and ECME steps, with goal to accelerate the convergence of the ECME algorithm. Both ECME and DORE algorithms aim at finding the maximum likelihood (ML) estimates of the unknown parameters assuming that the signal sparsity level is known. If the signal sparsity level is unknown, we propose an unconstrained sparsity selection (USS) criterion and show that, under certain conditions, maximizing the USS objective function with respect to the signal sparsity level is equivalent to finding the sparsest solution of the underlying underdetermined linear system. Our ADORE scheme demands no prior knowledge about the signal sparsity level and estimates this level by applying a golden-section search to maximize the USS objective function. We employ the proposed methods to reconstruct images from sparse tomographic projections and compare them with existing approaches that are feasible for large-scale data. Our numerical examples show that DORE is significantly faster than the ECME and related iterative hard thresholding (IHT) algorithms.

Published in:

Information Sciences and Systems (CISS), 2010 44th Annual Conference on

Date of Conference:

17-19 March 2010