Multiple random walkers and their application to image cosegmentation

Chulwoo Lee, Won Dong Jang, Jae Young Sim, Chang-Su Kim

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

47 Citations (Scopus)

Abstract

A graph-based system to simulate the movements and interactions of multiple random walkers (MRW) is proposed in this work. In the MRW system, multiple agents traverse a single graph simultaneously. To achieve desired interactions among those agents, a restart rule can be designed, which determines the restart distribution of each agent according to the probability distributions of all agents. In particular, we develop the repulsive rule for data clustering. We illustrate that the MRW clustering can segment real images reliably. Furthermore, we propose a novel image cosegmentation algorithm based on the MRW clustering. Specifically, the proposed algorithm consists of two steps: inter-image concurrence computation and intra-image MRW clustering. Experimental results demonstrate that the proposed algorithm provides promising cosegmentation performance.

Original languageEnglish
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE Computer Society
Pages3837-3845
Number of pages9
Volume07-12-June-2015
ISBN (Print)9781467369640
DOIs
Publication statusPublished - 2015 Oct 14
EventIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States
Duration: 2015 Jun 72015 Jun 12

Other

OtherIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
CountryUnited States
CityBoston
Period15/6/715/6/12

Fingerprint

Probability distributions

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Lee, C., Jang, W. D., Sim, J. Y., & Kim, C-S. (2015). Multiple random walkers and their application to image cosegmentation. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Vol. 07-12-June-2015, pp. 3837-3845). [7299008] IEEE Computer Society. https://doi.org/10.1109/CVPR.2015.7299008

Multiple random walkers and their application to image cosegmentation. / Lee, Chulwoo; Jang, Won Dong; Sim, Jae Young; Kim, Chang-Su.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 07-12-June-2015 IEEE Computer Society, 2015. p. 3837-3845 7299008.

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

Lee, C, Jang, WD, Sim, JY & Kim, C-S 2015, Multiple random walkers and their application to image cosegmentation. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. vol. 07-12-June-2015, 7299008, IEEE Computer Society, pp. 3837-3845, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, United States, 15/6/7. https://doi.org/10.1109/CVPR.2015.7299008
Lee C, Jang WD, Sim JY, Kim C-S. Multiple random walkers and their application to image cosegmentation. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 07-12-June-2015. IEEE Computer Society. 2015. p. 3837-3845. 7299008 https://doi.org/10.1109/CVPR.2015.7299008
Lee, Chulwoo ; Jang, Won Dong ; Sim, Jae Young ; Kim, Chang-Su. / Multiple random walkers and their application to image cosegmentation. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 07-12-June-2015 IEEE Computer Society, 2015. pp. 3837-3845
@inproceedings{9098ae6e346b4a49be871df77e64ce49,
title = "Multiple random walkers and their application to image cosegmentation",
abstract = "A graph-based system to simulate the movements and interactions of multiple random walkers (MRW) is proposed in this work. In the MRW system, multiple agents traverse a single graph simultaneously. To achieve desired interactions among those agents, a restart rule can be designed, which determines the restart distribution of each agent according to the probability distributions of all agents. In particular, we develop the repulsive rule for data clustering. We illustrate that the MRW clustering can segment real images reliably. Furthermore, we propose a novel image cosegmentation algorithm based on the MRW clustering. Specifically, the proposed algorithm consists of two steps: inter-image concurrence computation and intra-image MRW clustering. Experimental results demonstrate that the proposed algorithm provides promising cosegmentation performance.",
author = "Chulwoo Lee and Jang, {Won Dong} and Sim, {Jae Young} and Chang-Su Kim",
year = "2015",
month = "10",
day = "14",
doi = "10.1109/CVPR.2015.7299008",
language = "English",
isbn = "9781467369640",
volume = "07-12-June-2015",
pages = "3837--3845",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Multiple random walkers and their application to image cosegmentation

AU - Lee, Chulwoo

AU - Jang, Won Dong

AU - Sim, Jae Young

AU - Kim, Chang-Su

PY - 2015/10/14

Y1 - 2015/10/14

N2 - A graph-based system to simulate the movements and interactions of multiple random walkers (MRW) is proposed in this work. In the MRW system, multiple agents traverse a single graph simultaneously. To achieve desired interactions among those agents, a restart rule can be designed, which determines the restart distribution of each agent according to the probability distributions of all agents. In particular, we develop the repulsive rule for data clustering. We illustrate that the MRW clustering can segment real images reliably. Furthermore, we propose a novel image cosegmentation algorithm based on the MRW clustering. Specifically, the proposed algorithm consists of two steps: inter-image concurrence computation and intra-image MRW clustering. Experimental results demonstrate that the proposed algorithm provides promising cosegmentation performance.

AB - A graph-based system to simulate the movements and interactions of multiple random walkers (MRW) is proposed in this work. In the MRW system, multiple agents traverse a single graph simultaneously. To achieve desired interactions among those agents, a restart rule can be designed, which determines the restart distribution of each agent according to the probability distributions of all agents. In particular, we develop the repulsive rule for data clustering. We illustrate that the MRW clustering can segment real images reliably. Furthermore, we propose a novel image cosegmentation algorithm based on the MRW clustering. Specifically, the proposed algorithm consists of two steps: inter-image concurrence computation and intra-image MRW clustering. Experimental results demonstrate that the proposed algorithm provides promising cosegmentation performance.

UR - http://www.scopus.com/inward/record.url?scp=84959210628&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959210628&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2015.7299008

DO - 10.1109/CVPR.2015.7299008

M3 - Conference contribution

AN - SCOPUS:84959210628

SN - 9781467369640

VL - 07-12-June-2015

SP - 3837

EP - 3845

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

PB - IEEE Computer Society

ER -