Another stopping rule for linear iterative signal restoration

D. O. Walsh, Michael W Marcellin

Research output: Contribution to journalArticle

Abstract

A new stopping rule is proposed for linear, iterative signal restoration using the gradient descent and conjugate gradient algorithms. The stopping rule attempts to minimize MSE under the assumption that the signal arises from a white noise process. This assumption is appropriate for many coherent imaging applications. The stopping rule is trivial to compute and, for flxed relaxation parameters, can be computed prior to starting the iteration. The utility of the stopping rule is demonstrated through the restoration of MR imagery.

Original languageEnglish (US)
Pages (from-to)3156-3159
Number of pages4
JournalIEEE Transactions on Signal Processing
Volume47
Issue number11
DOIs
StatePublished - 1999

Fingerprint

Restoration
White noise
Imaging techniques

Keywords

  • Conjugate gradient, gradient descent, restoration, stopping rule

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing

Cite this

Another stopping rule for linear iterative signal restoration. / Walsh, D. O.; Marcellin, Michael W.

In: IEEE Transactions on Signal Processing, Vol. 47, No. 11, 1999, p. 3156-3159.

Research output: Contribution to journalArticle

@article{fc411d1a83504cf88acccc4ca32ff8d6,
title = "Another stopping rule for linear iterative signal restoration",
abstract = "A new stopping rule is proposed for linear, iterative signal restoration using the gradient descent and conjugate gradient algorithms. The stopping rule attempts to minimize MSE under the assumption that the signal arises from a white noise process. This assumption is appropriate for many coherent imaging applications. The stopping rule is trivial to compute and, for flxed relaxation parameters, can be computed prior to starting the iteration. The utility of the stopping rule is demonstrated through the restoration of MR imagery.",
keywords = "Conjugate gradient, gradient descent, restoration, stopping rule",
author = "Walsh, {D. O.} and Marcellin, {Michael W}",
year = "1999",
doi = "10.1109/78.796454",
language = "English (US)",
volume = "47",
pages = "3156--3159",
journal = "IEEE Transactions on Signal Processing",
issn = "1053-587X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "11",

}

TY - JOUR

T1 - Another stopping rule for linear iterative signal restoration

AU - Walsh, D. O.

AU - Marcellin, Michael W

PY - 1999

Y1 - 1999

N2 - A new stopping rule is proposed for linear, iterative signal restoration using the gradient descent and conjugate gradient algorithms. The stopping rule attempts to minimize MSE under the assumption that the signal arises from a white noise process. This assumption is appropriate for many coherent imaging applications. The stopping rule is trivial to compute and, for flxed relaxation parameters, can be computed prior to starting the iteration. The utility of the stopping rule is demonstrated through the restoration of MR imagery.

AB - A new stopping rule is proposed for linear, iterative signal restoration using the gradient descent and conjugate gradient algorithms. The stopping rule attempts to minimize MSE under the assumption that the signal arises from a white noise process. This assumption is appropriate for many coherent imaging applications. The stopping rule is trivial to compute and, for flxed relaxation parameters, can be computed prior to starting the iteration. The utility of the stopping rule is demonstrated through the restoration of MR imagery.

KW - Conjugate gradient, gradient descent, restoration, stopping rule

UR - http://www.scopus.com/inward/record.url?scp=0033221767&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033221767&partnerID=8YFLogxK

U2 - 10.1109/78.796454

DO - 10.1109/78.796454

M3 - Article

AN - SCOPUS:0033221767

VL - 47

SP - 3156

EP - 3159

JO - IEEE Transactions on Signal Processing

JF - IEEE Transactions on Signal Processing

SN - 1053-587X

IS - 11

ER -