Bayesian multiscale analysis of images modeled as Gaussian Markov random fields

Kevin Thon; Hvard Rue; Stein Olav Skrøvseth; Fred Godtliebsen

doi:10.1016/j.csda.2011.07.009

Bayesian multiscale analysis of images modeled as Gaussian Markov random fields

Kevin Thon, Hvard Rue, Stein Olav Skrøvseth^*, Fred Godtliebsen

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

18 Scopus citations

Abstract

A Bayesian multiscale technique for the detection of statistically significant features in noisy images is proposed. The prior is defined as a stationary intrinsic Gaussian Markov random field on a toroidal graph, which enables efficient computation of the relevant posterior marginals. Hence the method is applicable to large images produced by modern digital cameras. The technique is demonstrated in two examples from medical imaging.

Original language	English (US)
Pages (from-to)	49-61
Number of pages	13
Journal	Computational Statistics and Data Analysis
Volume	56
Issue number	1
DOIs	https://doi.org/10.1016/j.csda.2011.07.009
State	Published - Jan 1 2012
Externally published	Yes

Keywords

Bayesian analysis
Gaussian Markov random fields
Multi-resolution analysis
Scale space

ASJC Scopus subject areas

Statistics and Probability
Computational Mathematics
Computational Theory and Mathematics
Applied Mathematics

Access to Document

10.1016/j.csda.2011.07.009

Cite this

@article{27355f1ada40425da77b301437d8de25,

title = "Bayesian multiscale analysis of images modeled as Gaussian Markov random fields",

abstract = "A Bayesian multiscale technique for the detection of statistically significant features in noisy images is proposed. The prior is defined as a stationary intrinsic Gaussian Markov random field on a toroidal graph, which enables efficient computation of the relevant posterior marginals. Hence the method is applicable to large images produced by modern digital cameras. The technique is demonstrated in two examples from medical imaging.",

keywords = "Bayesian analysis, Gaussian Markov random fields, Multi-resolution analysis, Scale space",

author = "Kevin Thon and Hvard Rue and Skr{\o}vseth, {Stein Olav} and Fred Godtliebsen",

note = "Funding Information: We thank M.D. Thomas Schopf for sharing his expertise in dermatology, and Dr. med. Herbert Kirchesch for supplying us with the dermatoscopic skin lesion images used in the examples. We would also like to thank Dr. Maciel Zortea for doing the hair detection with the Dullrazor software. The research was funded by the Norwegian Research Council and the Centre for Research Driven Innovation, Troms{\o} Telemedicine Laboratory (TTL) .",

year = "2012",

month = jan,

day = "1",

doi = "10.1016/j.csda.2011.07.009",

language = "English (US)",

volume = "56",

pages = "49--61",

journal = "Computational Statistics and Data Analysis",

issn = "0167-9473",

publisher = "Elsevier",

number = "1",

}

TY - JOUR

T1 - Bayesian multiscale analysis of images modeled as Gaussian Markov random fields

AU - Thon, Kevin

AU - Rue, Hvard

AU - Skrøvseth, Stein Olav

AU - Godtliebsen, Fred

N1 - Funding Information: We thank M.D. Thomas Schopf for sharing his expertise in dermatology, and Dr. med. Herbert Kirchesch for supplying us with the dermatoscopic skin lesion images used in the examples. We would also like to thank Dr. Maciel Zortea for doing the hair detection with the Dullrazor software. The research was funded by the Norwegian Research Council and the Centre for Research Driven Innovation, Tromsø Telemedicine Laboratory (TTL) .

PY - 2012/1/1

Y1 - 2012/1/1

N2 - A Bayesian multiscale technique for the detection of statistically significant features in noisy images is proposed. The prior is defined as a stationary intrinsic Gaussian Markov random field on a toroidal graph, which enables efficient computation of the relevant posterior marginals. Hence the method is applicable to large images produced by modern digital cameras. The technique is demonstrated in two examples from medical imaging.

AB - A Bayesian multiscale technique for the detection of statistically significant features in noisy images is proposed. The prior is defined as a stationary intrinsic Gaussian Markov random field on a toroidal graph, which enables efficient computation of the relevant posterior marginals. Hence the method is applicable to large images produced by modern digital cameras. The technique is demonstrated in two examples from medical imaging.

KW - Bayesian analysis

KW - Gaussian Markov random fields

KW - Multi-resolution analysis

KW - Scale space

UR - http://www.scopus.com/inward/record.url?scp=80052024746&partnerID=8YFLogxK

U2 - 10.1016/j.csda.2011.07.009

DO - 10.1016/j.csda.2011.07.009

M3 - Article

AN - SCOPUS:80052024746

SN - 0167-9473

VL - 56

SP - 49

EP - 61

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

IS - 1

ER -

Bayesian multiscale analysis of images modeled as Gaussian Markov random fields

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this