Watershed-driven relaxation labeling for image segmentation

M. W. Hansen, William Evan Higgins

Research output: Contribution to journalConference article

14 Citations (Scopus)

Abstract

Introduces an image segmentation method referred to as watershed-driven relaxation labeling. The method is a hybrid segmentation process utilizing both watershed analysis and relaxation labeling. Initially, watershed analysis is used to subdivide an image into catchment basins, effectively clustering pixels together based on their spatial proximity and intensity homogeneity. Classification estimates in the form of probabilities are set for each of these catchment basins. Relaxation labeling is then used to iteratively refine and update the classifications of the catchment basins through propagating constraints and utilizing local information. The relaxation updating process is continued until a large majority of the catchment basins are unambiguously classified. The method provides fast, accurate segmentation results and exploits the individual strengths of watershed analysis and relaxation labeling. The robustness of the method is illustrated through comparisons to other popular segmentation techniques.

Original languageEnglish (US)
Article number413764
Pages (from-to)460-464
Number of pages5
JournalProceedings - International Conference on Image Processing, ICIP
Volume3
DOIs
StatePublished - Jan 1 1994
EventProceedings of the 1994 1st IEEE International Conference on Image Processing. Part 3 (of 3) - Austin, TX, USA
Duration: Nov 13 1994Nov 16 1994

Fingerprint

Watersheds
Image segmentation
Catchments
Labeling
Relaxation processes
Pixels

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

@article{80c004b6418f44b0a91d84720e7acb98,
title = "Watershed-driven relaxation labeling for image segmentation",
abstract = "Introduces an image segmentation method referred to as watershed-driven relaxation labeling. The method is a hybrid segmentation process utilizing both watershed analysis and relaxation labeling. Initially, watershed analysis is used to subdivide an image into catchment basins, effectively clustering pixels together based on their spatial proximity and intensity homogeneity. Classification estimates in the form of probabilities are set for each of these catchment basins. Relaxation labeling is then used to iteratively refine and update the classifications of the catchment basins through propagating constraints and utilizing local information. The relaxation updating process is continued until a large majority of the catchment basins are unambiguously classified. The method provides fast, accurate segmentation results and exploits the individual strengths of watershed analysis and relaxation labeling. The robustness of the method is illustrated through comparisons to other popular segmentation techniques.",
author = "Hansen, {M. W.} and Higgins, {William Evan}",
year = "1994",
month = "1",
day = "1",
doi = "10.1109/ICIP.1994.413764",
language = "English (US)",
volume = "3",
pages = "460--464",
journal = "Proceedings - International Conference on Image Processing, ICIP",
issn = "1522-4880",

}

Watershed-driven relaxation labeling for image segmentation. / Hansen, M. W.; Higgins, William Evan.

In: Proceedings - International Conference on Image Processing, ICIP, Vol. 3, 413764, 01.01.1994, p. 460-464.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Watershed-driven relaxation labeling for image segmentation

AU - Hansen, M. W.

AU - Higgins, William Evan

PY - 1994/1/1

Y1 - 1994/1/1

N2 - Introduces an image segmentation method referred to as watershed-driven relaxation labeling. The method is a hybrid segmentation process utilizing both watershed analysis and relaxation labeling. Initially, watershed analysis is used to subdivide an image into catchment basins, effectively clustering pixels together based on their spatial proximity and intensity homogeneity. Classification estimates in the form of probabilities are set for each of these catchment basins. Relaxation labeling is then used to iteratively refine and update the classifications of the catchment basins through propagating constraints and utilizing local information. The relaxation updating process is continued until a large majority of the catchment basins are unambiguously classified. The method provides fast, accurate segmentation results and exploits the individual strengths of watershed analysis and relaxation labeling. The robustness of the method is illustrated through comparisons to other popular segmentation techniques.

AB - Introduces an image segmentation method referred to as watershed-driven relaxation labeling. The method is a hybrid segmentation process utilizing both watershed analysis and relaxation labeling. Initially, watershed analysis is used to subdivide an image into catchment basins, effectively clustering pixels together based on their spatial proximity and intensity homogeneity. Classification estimates in the form of probabilities are set for each of these catchment basins. Relaxation labeling is then used to iteratively refine and update the classifications of the catchment basins through propagating constraints and utilizing local information. The relaxation updating process is continued until a large majority of the catchment basins are unambiguously classified. The method provides fast, accurate segmentation results and exploits the individual strengths of watershed analysis and relaxation labeling. The robustness of the method is illustrated through comparisons to other popular segmentation techniques.

UR - http://www.scopus.com/inward/record.url?scp=84999836141&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84999836141&partnerID=8YFLogxK

U2 - 10.1109/ICIP.1994.413764

DO - 10.1109/ICIP.1994.413764

M3 - Conference article

VL - 3

SP - 460

EP - 464

JO - Proceedings - International Conference on Image Processing, ICIP

JF - Proceedings - International Conference on Image Processing, ICIP

SN - 1522-4880

M1 - 413764

ER -