Bilateral Markov mesh random field and its application to image restoration

Siamak Yousefi, N. Kehtarnavaz, Y. Cao, Q. R. Razlighi

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

This paper introduces bilateral Markov mesh random field to overcome the shortcomings of the conventional Markov random fields in image modeling. These shortcomings consist of (a) the computational intractability of such fields when expressing the image probability function in the form of the Gibbs distribution function, and (b) the formulation of the image probability function via the product of low-dimensional densities at the expense of obtaining non-symmetrical image models. The properties of bilateral Markov mesh random field are presented and used to derive an image model to address the above shortcomings. As an application, a framework for image restoration is then provided. Restoration results based on this new bilateral Markov mesh random field are compared to the conventional fields to demonstrate its effectiveness.

Original languageEnglish (US)
Pages (from-to)1051-1059
Number of pages9
JournalJournal of Visual Communication and Image Representation
Volume23
Issue number7
DOIs
StatePublished - Oct 1 2012

Fingerprint

Image reconstruction
Restoration
Distribution functions

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Media Technology
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Bilateral Markov mesh random field and its application to image restoration. / Yousefi, Siamak; Kehtarnavaz, N.; Cao, Y.; Razlighi, Q. R.

In: Journal of Visual Communication and Image Representation, Vol. 23, No. 7, 01.10.2012, p. 1051-1059.

Research output: Contribution to journalArticle

@article{31ce6832473b43cd944d719ae09aafa9,
title = "Bilateral Markov mesh random field and its application to image restoration",
abstract = "This paper introduces bilateral Markov mesh random field to overcome the shortcomings of the conventional Markov random fields in image modeling. These shortcomings consist of (a) the computational intractability of such fields when expressing the image probability function in the form of the Gibbs distribution function, and (b) the formulation of the image probability function via the product of low-dimensional densities at the expense of obtaining non-symmetrical image models. The properties of bilateral Markov mesh random field are presented and used to derive an image model to address the above shortcomings. As an application, a framework for image restoration is then provided. Restoration results based on this new bilateral Markov mesh random field are compared to the conventional fields to demonstrate its effectiveness.",
author = "Siamak Yousefi and N. Kehtarnavaz and Y. Cao and Razlighi, {Q. R.}",
year = "2012",
month = "10",
day = "1",
doi = "10.1016/j.jvcir.2012.06.001",
language = "English (US)",
volume = "23",
pages = "1051--1059",
journal = "Journal of Visual Communication and Image Representation",
issn = "1047-3203",
publisher = "Academic Press Inc.",
number = "7",

}

TY - JOUR

T1 - Bilateral Markov mesh random field and its application to image restoration

AU - Yousefi, Siamak

AU - Kehtarnavaz, N.

AU - Cao, Y.

AU - Razlighi, Q. R.

PY - 2012/10/1

Y1 - 2012/10/1

N2 - This paper introduces bilateral Markov mesh random field to overcome the shortcomings of the conventional Markov random fields in image modeling. These shortcomings consist of (a) the computational intractability of such fields when expressing the image probability function in the form of the Gibbs distribution function, and (b) the formulation of the image probability function via the product of low-dimensional densities at the expense of obtaining non-symmetrical image models. The properties of bilateral Markov mesh random field are presented and used to derive an image model to address the above shortcomings. As an application, a framework for image restoration is then provided. Restoration results based on this new bilateral Markov mesh random field are compared to the conventional fields to demonstrate its effectiveness.

AB - This paper introduces bilateral Markov mesh random field to overcome the shortcomings of the conventional Markov random fields in image modeling. These shortcomings consist of (a) the computational intractability of such fields when expressing the image probability function in the form of the Gibbs distribution function, and (b) the formulation of the image probability function via the product of low-dimensional densities at the expense of obtaining non-symmetrical image models. The properties of bilateral Markov mesh random field are presented and used to derive an image model to address the above shortcomings. As an application, a framework for image restoration is then provided. Restoration results based on this new bilateral Markov mesh random field are compared to the conventional fields to demonstrate its effectiveness.

UR - http://www.scopus.com/inward/record.url?scp=84864129550&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864129550&partnerID=8YFLogxK

U2 - 10.1016/j.jvcir.2012.06.001

DO - 10.1016/j.jvcir.2012.06.001

M3 - Article

VL - 23

SP - 1051

EP - 1059

JO - Journal of Visual Communication and Image Representation

JF - Journal of Visual Communication and Image Representation

SN - 1047-3203

IS - 7

ER -