A multiagent system approach for image segmentation using genetic algorithms and extremal optimization heuristics

Kamal E. Melkemi, Mohamed Batouche, Sebti Foufou

Research output: Contribution to journalArticle

Abstract

We propose a new distributed image segmentation algorithm structured as a multiagent system composed of a set of segmentation agents and a coordinator agent. Starting from its own initial image, each segmentation agent performs the iterated conditional modes method, known as ICM, in applications based on Markov random fields, to obtain a sub-optimal segmented image. The coordinator agent diversifies the initial images using the genetic crossover and mutation operators along with the extremal optimization local search. This combination increases the efficiency of our algorithm and ensures its convergence to an optimal segmentation as it is shown through some experimental results.

Original languageEnglish (US)
Pages (from-to)1230-1238
Number of pages9
JournalPattern Recognition Letters
Volume27
Issue number11
DOIs
StatePublished - Aug 1 2006

Fingerprint

Multi agent systems
Image segmentation
Genetic algorithms
Mathematical operators

Keywords

  • Extremal optimization
  • Genetic algorithms
  • Image segmentation
  • Markov random fields
  • Multiagent systems

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

A multiagent system approach for image segmentation using genetic algorithms and extremal optimization heuristics. / Melkemi, Kamal E.; Batouche, Mohamed; Foufou, Sebti.

In: Pattern Recognition Letters, Vol. 27, No. 11, 01.08.2006, p. 1230-1238.

Research output: Contribution to journalArticle

@article{b34509dcfcdd44698d4bc7080966b865,
title = "A multiagent system approach for image segmentation using genetic algorithms and extremal optimization heuristics",
abstract = "We propose a new distributed image segmentation algorithm structured as a multiagent system composed of a set of segmentation agents and a coordinator agent. Starting from its own initial image, each segmentation agent performs the iterated conditional modes method, known as ICM, in applications based on Markov random fields, to obtain a sub-optimal segmented image. The coordinator agent diversifies the initial images using the genetic crossover and mutation operators along with the extremal optimization local search. This combination increases the efficiency of our algorithm and ensures its convergence to an optimal segmentation as it is shown through some experimental results.",
keywords = "Extremal optimization, Genetic algorithms, Image segmentation, Markov random fields, Multiagent systems",
author = "Melkemi, {Kamal E.} and Mohamed Batouche and Sebti Foufou",
year = "2006",
month = "8",
day = "1",
doi = "10.1016/j.patrec.2005.07.021",
language = "English (US)",
volume = "27",
pages = "1230--1238",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",
number = "11",

}

TY - JOUR

T1 - A multiagent system approach for image segmentation using genetic algorithms and extremal optimization heuristics

AU - Melkemi, Kamal E.

AU - Batouche, Mohamed

AU - Foufou, Sebti

PY - 2006/8/1

Y1 - 2006/8/1

N2 - We propose a new distributed image segmentation algorithm structured as a multiagent system composed of a set of segmentation agents and a coordinator agent. Starting from its own initial image, each segmentation agent performs the iterated conditional modes method, known as ICM, in applications based on Markov random fields, to obtain a sub-optimal segmented image. The coordinator agent diversifies the initial images using the genetic crossover and mutation operators along with the extremal optimization local search. This combination increases the efficiency of our algorithm and ensures its convergence to an optimal segmentation as it is shown through some experimental results.

AB - We propose a new distributed image segmentation algorithm structured as a multiagent system composed of a set of segmentation agents and a coordinator agent. Starting from its own initial image, each segmentation agent performs the iterated conditional modes method, known as ICM, in applications based on Markov random fields, to obtain a sub-optimal segmented image. The coordinator agent diversifies the initial images using the genetic crossover and mutation operators along with the extremal optimization local search. This combination increases the efficiency of our algorithm and ensures its convergence to an optimal segmentation as it is shown through some experimental results.

KW - Extremal optimization

KW - Genetic algorithms

KW - Image segmentation

KW - Markov random fields

KW - Multiagent systems

UR - http://www.scopus.com/inward/record.url?scp=33646708051&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33646708051&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2005.07.021

DO - 10.1016/j.patrec.2005.07.021

M3 - Article

AN - SCOPUS:33646708051

VL - 27

SP - 1230

EP - 1238

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

IS - 11

ER -