Globally optimal regions and boundaries

Ian H. Jermyn, Hiroshi Ishikawa

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

26 Citations (Scopus)

Abstract

We propose a new form of energy functional for the segmentation of regions in images, and an efficient method for finding its global optima. The energy can have contributions from both the region and its boundary, thus combining the best features of region- and boundary-based approaches to segmentation. By transforming the region energy into a boundary energy, we can treat both contributions on an equal footing, and solve the global optimization problem as a minimum mean weight cycle problem on a directed graph. The simple, polynomial-time algorithm requires no initialization and is highly parallelizable.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Computer Vision
Place of PublicationPiscataway, NJ, United States
PublisherIEEE
Pages904-910
Number of pages7
Volume2
Publication statusPublished - 1999
Externally publishedYes
EventProceedings of the 1999 7th IEEE International Conference on Computer Vision (ICCV'99) - Kerkyra, Greece
Duration: 1999 Sep 201999 Sep 27

Other

OtherProceedings of the 1999 7th IEEE International Conference on Computer Vision (ICCV'99)
CityKerkyra, Greece
Period99/9/2099/9/27

Fingerprint

Directed graphs
Global optimization
Polynomials

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Software

Cite this

Jermyn, I. H., & Ishikawa, H. (1999). Globally optimal regions and boundaries. In Proceedings of the IEEE International Conference on Computer Vision (Vol. 2, pp. 904-910). Piscataway, NJ, United States: IEEE.

Globally optimal regions and boundaries. / Jermyn, Ian H.; Ishikawa, Hiroshi.

Proceedings of the IEEE International Conference on Computer Vision. Vol. 2 Piscataway, NJ, United States : IEEE, 1999. p. 904-910.

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

Jermyn, IH & Ishikawa, H 1999, Globally optimal regions and boundaries. in Proceedings of the IEEE International Conference on Computer Vision. vol. 2, IEEE, Piscataway, NJ, United States, pp. 904-910, Proceedings of the 1999 7th IEEE International Conference on Computer Vision (ICCV'99), Kerkyra, Greece, 99/9/20.
Jermyn IH, Ishikawa H. Globally optimal regions and boundaries. In Proceedings of the IEEE International Conference on Computer Vision. Vol. 2. Piscataway, NJ, United States: IEEE. 1999. p. 904-910
Jermyn, Ian H. ; Ishikawa, Hiroshi. / Globally optimal regions and boundaries. Proceedings of the IEEE International Conference on Computer Vision. Vol. 2 Piscataway, NJ, United States : IEEE, 1999. pp. 904-910
@inproceedings{4f23999fdb384482aac11f084e047ac2,
title = "Globally optimal regions and boundaries",
abstract = "We propose a new form of energy functional for the segmentation of regions in images, and an efficient method for finding its global optima. The energy can have contributions from both the region and its boundary, thus combining the best features of region- and boundary-based approaches to segmentation. By transforming the region energy into a boundary energy, we can treat both contributions on an equal footing, and solve the global optimization problem as a minimum mean weight cycle problem on a directed graph. The simple, polynomial-time algorithm requires no initialization and is highly parallelizable.",
author = "Jermyn, {Ian H.} and Hiroshi Ishikawa",
year = "1999",
language = "English",
volume = "2",
pages = "904--910",
booktitle = "Proceedings of the IEEE International Conference on Computer Vision",
publisher = "IEEE",

}

TY - GEN

T1 - Globally optimal regions and boundaries

AU - Jermyn, Ian H.

AU - Ishikawa, Hiroshi

PY - 1999

Y1 - 1999

N2 - We propose a new form of energy functional for the segmentation of regions in images, and an efficient method for finding its global optima. The energy can have contributions from both the region and its boundary, thus combining the best features of region- and boundary-based approaches to segmentation. By transforming the region energy into a boundary energy, we can treat both contributions on an equal footing, and solve the global optimization problem as a minimum mean weight cycle problem on a directed graph. The simple, polynomial-time algorithm requires no initialization and is highly parallelizable.

AB - We propose a new form of energy functional for the segmentation of regions in images, and an efficient method for finding its global optima. The energy can have contributions from both the region and its boundary, thus combining the best features of region- and boundary-based approaches to segmentation. By transforming the region energy into a boundary energy, we can treat both contributions on an equal footing, and solve the global optimization problem as a minimum mean weight cycle problem on a directed graph. The simple, polynomial-time algorithm requires no initialization and is highly parallelizable.

UR - http://www.scopus.com/inward/record.url?scp=0033283824&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033283824&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0033283824

VL - 2

SP - 904

EP - 910

BT - Proceedings of the IEEE International Conference on Computer Vision

PB - IEEE

CY - Piscataway, NJ, United States

ER -