Skip to Main content Skip to Navigation
Theses

Conception de métaheuristiques d'optimisation pour la segmentation d'images : application aux images IRM du cerveau et aux images de tomographie par émission de positons

Abstract : Image segmentation is the process of partitioning a digital image into homogeneous non-overlapped regions with respect to some characteristics, such as gray value, motion, texture, etc. It is used in various applications like medical imaging, objects detection, biometric system, remote sensing, robot navigation, video surveillance, etc. The success of the machine vision system depends heavily on its performance, because characteristics and decisions are extracted and taken from its result. The first image segmentation algorithms were introduced in the 70's. Since then, various techniques and methods were experimented to improve the results. Nevertheless, up till now, no method produces a perfect result for a wide variety of images. Metaheuristics are a high level procedure designed to solve hard optimization problems. These problems are in general characterized by their incomplete, uncertain or noised data, or faced to low computing capacity. Metaheuristics have been extremely successful in a wide variety of fields and demonstrate significant results. This is due to the fact that they can applied to solve any problem which can be formulated as an optimization problem. These methods are, mainly, inspired from physics (simulated annealing), biology (evolutionary algorithms), or ethology (particle swarm optimization, ant colony optimization).In recent years, metaheuristics are starting to be exploited to solve segmentation problems with varying degrees of success and allow to consider the problem with different perspectives. Bearing this in mind, we propose in this work three segmentation and post-segmentation approaches based on mono or multiobjective optimization metaheuristics. The proposed methods were evaluated on databases containing synthetic images, simulated MRI images, real MRI images and PET images. The obtained results show the efficiency of the proposed ideas
Document type :
Theses
Complete list of metadata

Cited literature [100 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-01143778
Contributor : Abes Star :  Contact
Submitted on : Monday, April 20, 2015 - 11:12:05 AM
Last modification on : Friday, October 4, 2019 - 1:10:28 AM

File

TH2014PEST1106_archivage.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01143778, version 1

Collections

Citation

Ahmed Nasreddine Benaichouche. Conception de métaheuristiques d'optimisation pour la segmentation d'images : application aux images IRM du cerveau et aux images de tomographie par émission de positons. Analyse numérique [cs.NA]. Université Paris-Est, 2014. Français. ⟨NNT : 2014PEST1106⟩. ⟨tel-01143778⟩

Share

Metrics

Record views

1177

Files downloads

9829