Markov random field model-based approach to image interpretation

J. W. Modestino, J. Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Citations (Scopus)

Abstract

A Markov random field (MRF) model-based approach to automated image interpretation is described and demonstrated as a region-based scheme. In this approach, an image is first segemented into a collection of disjoint regions which form the nodes of an adjacency graph. Image interpretation is then achieved through assigning object labels, or interpretations, to the segmented regions, or nodes, using domain knowledge, extracted feature measurements, and spatial relationships between the various regions. The interpretation labels are modeled as a MRF on the corresponding adjacency graph, and the image interpretation problem are formulated as a maximum a posteriori (MAP) estimation rule. Simulated annealing is used to find the best realization, or optimal interpretation. Through the MRF model, this approach also provides a systematic method for organizing and representing domain knowledge through the clique functions of the probability density function underlying MRF. Results of image interpretation experiments performed on synthetic and real-world images using this approach are described.

Original languageEnglish
Title of host publicationUnknown Host Publication Title
Editors Anon
Place of PublicationPiscataway, NJ, United States
PublisherPubl by IEEE
Pages458-465
Number of pages8
StatePublished - Dec 1 1989
EventProceedings: IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Rosemont, IL, USA
Duration: Jun 6 1989Jun 9 1989

Other

OtherProceedings: IEEE Computer Society Conference on Computer Vision and Pattern Recognition
CityRosemont, IL, USA
Period6/6/896/9/89

Fingerprint

Labels
Simulated annealing
Probability density function
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Modestino, J. W., & Zhang, J. (1989). Markov random field model-based approach to image interpretation. In Anon (Ed.), Unknown Host Publication Title (pp. 458-465). Piscataway, NJ, United States: Publ by IEEE.

Markov random field model-based approach to image interpretation. / Modestino, J. W.; Zhang, J.

Unknown Host Publication Title. ed. / Anon. Piscataway, NJ, United States : Publ by IEEE, 1989. p. 458-465.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Modestino, JW & Zhang, J 1989, Markov random field model-based approach to image interpretation. in Anon (ed.), Unknown Host Publication Title. Publ by IEEE, Piscataway, NJ, United States, pp. 458-465, Proceedings: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Rosemont, IL, USA, 6/6/89.
Modestino JW, Zhang J. Markov random field model-based approach to image interpretation. In Anon, editor, Unknown Host Publication Title. Piscataway, NJ, United States: Publ by IEEE. 1989. p. 458-465
Modestino, J. W. ; Zhang, J. / Markov random field model-based approach to image interpretation. Unknown Host Publication Title. editor / Anon. Piscataway, NJ, United States : Publ by IEEE, 1989. pp. 458-465
@inproceedings{3bf1100b52514a0ba630895ff022dd7b,
title = "Markov random field model-based approach to image interpretation",
abstract = "A Markov random field (MRF) model-based approach to automated image interpretation is described and demonstrated as a region-based scheme. In this approach, an image is first segemented into a collection of disjoint regions which form the nodes of an adjacency graph. Image interpretation is then achieved through assigning object labels, or interpretations, to the segmented regions, or nodes, using domain knowledge, extracted feature measurements, and spatial relationships between the various regions. The interpretation labels are modeled as a MRF on the corresponding adjacency graph, and the image interpretation problem are formulated as a maximum a posteriori (MAP) estimation rule. Simulated annealing is used to find the best realization, or optimal interpretation. Through the MRF model, this approach also provides a systematic method for organizing and representing domain knowledge through the clique functions of the probability density function underlying MRF. Results of image interpretation experiments performed on synthetic and real-world images using this approach are described.",
author = "Modestino, {J. W.} and J. Zhang",
year = "1989",
month = "12",
day = "1",
language = "English",
pages = "458--465",
editor = "Anon",
booktitle = "Unknown Host Publication Title",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Markov random field model-based approach to image interpretation

AU - Modestino, J. W.

AU - Zhang, J.

PY - 1989/12/1

Y1 - 1989/12/1

N2 - A Markov random field (MRF) model-based approach to automated image interpretation is described and demonstrated as a region-based scheme. In this approach, an image is first segemented into a collection of disjoint regions which form the nodes of an adjacency graph. Image interpretation is then achieved through assigning object labels, or interpretations, to the segmented regions, or nodes, using domain knowledge, extracted feature measurements, and spatial relationships between the various regions. The interpretation labels are modeled as a MRF on the corresponding adjacency graph, and the image interpretation problem are formulated as a maximum a posteriori (MAP) estimation rule. Simulated annealing is used to find the best realization, or optimal interpretation. Through the MRF model, this approach also provides a systematic method for organizing and representing domain knowledge through the clique functions of the probability density function underlying MRF. Results of image interpretation experiments performed on synthetic and real-world images using this approach are described.

AB - A Markov random field (MRF) model-based approach to automated image interpretation is described and demonstrated as a region-based scheme. In this approach, an image is first segemented into a collection of disjoint regions which form the nodes of an adjacency graph. Image interpretation is then achieved through assigning object labels, or interpretations, to the segmented regions, or nodes, using domain knowledge, extracted feature measurements, and spatial relationships between the various regions. The interpretation labels are modeled as a MRF on the corresponding adjacency graph, and the image interpretation problem are formulated as a maximum a posteriori (MAP) estimation rule. Simulated annealing is used to find the best realization, or optimal interpretation. Through the MRF model, this approach also provides a systematic method for organizing and representing domain knowledge through the clique functions of the probability density function underlying MRF. Results of image interpretation experiments performed on synthetic and real-world images using this approach are described.

UR - http://www.scopus.com/inward/record.url?scp=0024860907&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024860907&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0024860907

SP - 458

EP - 465

BT - Unknown Host Publication Title

A2 - Anon, null

PB - Publ by IEEE

CY - Piscataway, NJ, United States

ER -