Medical image segmentation using the combination of watershed and FCM clustering algorithms

Wen Feng Kuo, Chi Yuan Lin, Wei Yen Hsu

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

In this study, a new image segmentation technique that combines watershed algorithm and fuzzy clustering algorithms is proposed to minimize undesirable oversegmentation. Watershed algorithm invariably produces over-segmentation due to noise or local irregularities in the gradient images. In the proposed scheme, first, it presents a region merging method based on employing the Markov Random Field (MRF) model on the Region Adjacency Graph (RAG) to refine the quality of watershed algorithm, and then, the relationship of inter-region similarities is then performed by involving the spatial domain (watershed) and feature spaces (clustering) into image mapping in order to determine optimal region merging. To obtain the spatial domain and feature spaces representation of the image, spatial graph representation is used, which is derived from the watershed partitioning and feature spaces representation acquired from the Fuzzy C-Means (FCM) clustering technique. Experimental results show that the proposed technique gives more promising segmentation results in comparison with the conventional watershed algorithm by means of the assessment of several brain phantom and real data.

Original languageEnglish
Pages (from-to)5255-5267
Number of pages13
JournalInternational Journal of Innovative Computing, Information and Control
Volume7
Issue number9
Publication statusPublished - Sep 2011
Externally publishedYes

Fingerprint

Fuzzy C-means Clustering
Medical Image
Watersheds
Image segmentation
Clustering algorithms
Image Segmentation
Clustering Algorithm
Feature Space
Merging
Segmentation
Spatial Graph
Graph Representation
Fuzzy Algorithm
Fuzzy clustering
Adjacency
Fuzzy Clustering
Irregularity
Phantom
Random Field
Partitioning

Keywords

  • Clustering
  • Fuzzy c-means
  • Image segmentation
  • Region adjacency graph
  • Watershed

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Information Systems
  • Software
  • Theoretical Computer Science

Cite this

Medical image segmentation using the combination of watershed and FCM clustering algorithms. / Kuo, Wen Feng; Lin, Chi Yuan; Hsu, Wei Yen.

In: International Journal of Innovative Computing, Information and Control, Vol. 7, No. 9, 09.2011, p. 5255-5267.

Research output: Contribution to journalArticle

@article{ee7ab1f8c49e4d0c9209f51033603ebe,
title = "Medical image segmentation using the combination of watershed and FCM clustering algorithms",
abstract = "In this study, a new image segmentation technique that combines watershed algorithm and fuzzy clustering algorithms is proposed to minimize undesirable oversegmentation. Watershed algorithm invariably produces over-segmentation due to noise or local irregularities in the gradient images. In the proposed scheme, first, it presents a region merging method based on employing the Markov Random Field (MRF) model on the Region Adjacency Graph (RAG) to refine the quality of watershed algorithm, and then, the relationship of inter-region similarities is then performed by involving the spatial domain (watershed) and feature spaces (clustering) into image mapping in order to determine optimal region merging. To obtain the spatial domain and feature spaces representation of the image, spatial graph representation is used, which is derived from the watershed partitioning and feature spaces representation acquired from the Fuzzy C-Means (FCM) clustering technique. Experimental results show that the proposed technique gives more promising segmentation results in comparison with the conventional watershed algorithm by means of the assessment of several brain phantom and real data.",
keywords = "Clustering, Fuzzy c-means, Image segmentation, Region adjacency graph, Watershed",
author = "Kuo, {Wen Feng} and Lin, {Chi Yuan} and Hsu, {Wei Yen}",
year = "2011",
month = "9",
language = "English",
volume = "7",
pages = "5255--5267",
journal = "International Journal of Innovative Computing, Information and Control",
issn = "1349-4198",
publisher = "IJICIC Editorial Office",
number = "9",

}

TY - JOUR

T1 - Medical image segmentation using the combination of watershed and FCM clustering algorithms

AU - Kuo, Wen Feng

AU - Lin, Chi Yuan

AU - Hsu, Wei Yen

PY - 2011/9

Y1 - 2011/9

N2 - In this study, a new image segmentation technique that combines watershed algorithm and fuzzy clustering algorithms is proposed to minimize undesirable oversegmentation. Watershed algorithm invariably produces over-segmentation due to noise or local irregularities in the gradient images. In the proposed scheme, first, it presents a region merging method based on employing the Markov Random Field (MRF) model on the Region Adjacency Graph (RAG) to refine the quality of watershed algorithm, and then, the relationship of inter-region similarities is then performed by involving the spatial domain (watershed) and feature spaces (clustering) into image mapping in order to determine optimal region merging. To obtain the spatial domain and feature spaces representation of the image, spatial graph representation is used, which is derived from the watershed partitioning and feature spaces representation acquired from the Fuzzy C-Means (FCM) clustering technique. Experimental results show that the proposed technique gives more promising segmentation results in comparison with the conventional watershed algorithm by means of the assessment of several brain phantom and real data.

AB - In this study, a new image segmentation technique that combines watershed algorithm and fuzzy clustering algorithms is proposed to minimize undesirable oversegmentation. Watershed algorithm invariably produces over-segmentation due to noise or local irregularities in the gradient images. In the proposed scheme, first, it presents a region merging method based on employing the Markov Random Field (MRF) model on the Region Adjacency Graph (RAG) to refine the quality of watershed algorithm, and then, the relationship of inter-region similarities is then performed by involving the spatial domain (watershed) and feature spaces (clustering) into image mapping in order to determine optimal region merging. To obtain the spatial domain and feature spaces representation of the image, spatial graph representation is used, which is derived from the watershed partitioning and feature spaces representation acquired from the Fuzzy C-Means (FCM) clustering technique. Experimental results show that the proposed technique gives more promising segmentation results in comparison with the conventional watershed algorithm by means of the assessment of several brain phantom and real data.

KW - Clustering

KW - Fuzzy c-means

KW - Image segmentation

KW - Region adjacency graph

KW - Watershed

UR - http://www.scopus.com/inward/record.url?scp=79961061603&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79961061603&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:79961061603

VL - 7

SP - 5255

EP - 5267

JO - International Journal of Innovative Computing, Information and Control

JF - International Journal of Innovative Computing, Information and Control

SN - 1349-4198

IS - 9

ER -