Region similarity relationship between watershed and penalized fuzzy hopfield neural network algorithms for brain image segmentation

Wen Feng Kuo, Chi Yuan Lin, Yung-Nien Sun

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

A robust image segmentation method that combines the watershed segmentation and penalized fuzzy Hopfield neural network (PFHNN) algorithms to minimize undesirable over-segmentation is described in this paper. This method incorporates spatial graph representation derived from the watershed segmented regions and cluster analysis information obtained from the PFHNN algorithm to achieve efficient image segmentation. The proposed scheme employs the Markov random field (MRF) model on the region adjacency graph (RAG) to improve the quality of watershed segmentation. Here, the fusion criterion is according to the correlation coefficient, which uses inter-region similarities to determine the merging of regions. Analysis of the performance of the proposed technique is presented through quantitative and qualitative validation experiments on benchmark images, and significant and promising segmentation results are presented using brain phantom simulated data.

Original languageEnglish
Pages (from-to)1403-1425
Number of pages23
JournalInternational Journal of Pattern Recognition and Artificial Intelligence
Volume22
Issue number7
DOIs
Publication statusPublished - 2008 Nov 1

Fingerprint

Hopfield neural networks
Fuzzy neural networks
Watersheds
Image segmentation
Brain
Cluster analysis
Merging
Fusion reactions
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Software

Cite this

@article{ca1b21346d2340dd8de3b85dcbba94a9,
title = "Region similarity relationship between watershed and penalized fuzzy hopfield neural network algorithms for brain image segmentation",
abstract = "A robust image segmentation method that combines the watershed segmentation and penalized fuzzy Hopfield neural network (PFHNN) algorithms to minimize undesirable over-segmentation is described in this paper. This method incorporates spatial graph representation derived from the watershed segmented regions and cluster analysis information obtained from the PFHNN algorithm to achieve efficient image segmentation. The proposed scheme employs the Markov random field (MRF) model on the region adjacency graph (RAG) to improve the quality of watershed segmentation. Here, the fusion criterion is according to the correlation coefficient, which uses inter-region similarities to determine the merging of regions. Analysis of the performance of the proposed technique is presented through quantitative and qualitative validation experiments on benchmark images, and significant and promising segmentation results are presented using brain phantom simulated data.",
author = "Kuo, {Wen Feng} and Lin, {Chi Yuan} and Yung-Nien Sun",
year = "2008",
month = "11",
day = "1",
doi = "10.1142/S0218001408006788",
language = "English",
volume = "22",
pages = "1403--1425",
journal = "International Journal of Pattern Recognition and Artificial Intelligence",
issn = "0218-0014",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "7",

}

TY - JOUR

T1 - Region similarity relationship between watershed and penalized fuzzy hopfield neural network algorithms for brain image segmentation

AU - Kuo, Wen Feng

AU - Lin, Chi Yuan

AU - Sun, Yung-Nien

PY - 2008/11/1

Y1 - 2008/11/1

N2 - A robust image segmentation method that combines the watershed segmentation and penalized fuzzy Hopfield neural network (PFHNN) algorithms to minimize undesirable over-segmentation is described in this paper. This method incorporates spatial graph representation derived from the watershed segmented regions and cluster analysis information obtained from the PFHNN algorithm to achieve efficient image segmentation. The proposed scheme employs the Markov random field (MRF) model on the region adjacency graph (RAG) to improve the quality of watershed segmentation. Here, the fusion criterion is according to the correlation coefficient, which uses inter-region similarities to determine the merging of regions. Analysis of the performance of the proposed technique is presented through quantitative and qualitative validation experiments on benchmark images, and significant and promising segmentation results are presented using brain phantom simulated data.

AB - A robust image segmentation method that combines the watershed segmentation and penalized fuzzy Hopfield neural network (PFHNN) algorithms to minimize undesirable over-segmentation is described in this paper. This method incorporates spatial graph representation derived from the watershed segmented regions and cluster analysis information obtained from the PFHNN algorithm to achieve efficient image segmentation. The proposed scheme employs the Markov random field (MRF) model on the region adjacency graph (RAG) to improve the quality of watershed segmentation. Here, the fusion criterion is according to the correlation coefficient, which uses inter-region similarities to determine the merging of regions. Analysis of the performance of the proposed technique is presented through quantitative and qualitative validation experiments on benchmark images, and significant and promising segmentation results are presented using brain phantom simulated data.

UR - http://www.scopus.com/inward/record.url?scp=58449090923&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=58449090923&partnerID=8YFLogxK

U2 - 10.1142/S0218001408006788

DO - 10.1142/S0218001408006788

M3 - Article

VL - 22

SP - 1403

EP - 1425

JO - International Journal of Pattern Recognition and Artificial Intelligence

JF - International Journal of Pattern Recognition and Artificial Intelligence

SN - 0218-0014

IS - 7

ER -