Particle Based Image Segmentation with Simulated Annealing

M.H. Everts; H. Bekker; A.C. Jalba; J.B.T.M. Roerdink

Particle Based Image Segmentation with Simulated Annealing

M.H. Everts, H. Bekker, A.C. Jalba, J.B.T.M. Roerdink

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic

255 Downloads (Pure)

Abstract

The Charged Particle Model (CPM) is a physically motivated deformable model for shape recovery and segmentation. It simulates a system of charged particles moving in an electric field generated from the input image, whose positions in the equilibrium state are used for curve or surface reconstruction. As an alternative we propose to use simulated annealing to position these particles and present a fast and simple algorithm that is able to match CPM’s results on images with well defined contours.

Original language	English
Title of host publication	EPRINTS-BOOK-TITLE
Publisher	University of Groningen, Johann Bernoulli Institute for Mathematics and Computer Science
Number of pages	7
Publication status	Published - 2007

Keywords

simulated annealing
particle systems
image segmentation

Access to Document

2007ProcASCIEverts.pdfFinal publisher's version, 1.34 MB

Handle.net

Persistent link

Cite this

@inbook{6e232cf4b16b44778793e9424b7a6747,

title = "Particle Based Image Segmentation with Simulated Annealing",

abstract = "The Charged Particle Model (CPM) is a physically motivated deformable model for shape recovery and segmentation. It simulates a system of charged particles moving in an electric field generated from the input image, whose positions in the equilibrium state are used for curve or surface reconstruction. As an alternative we propose to use simulated annealing to position these particles and present a fast and simple algorithm that is able to match CPM{\textquoteright}s results on images with well defined contours.",

keywords = "simulated annealing, particle systems, image segmentation",

author = "M.H. Everts and H. Bekker and A.C. Jalba and J.B.T.M. Roerdink",

note = "Relation: http://www.rug.nl/informatica/organisatie/overorganisatie/iwi Rights: University of Groningen. Research Institute for Mathematics and Computing Science (IWI)",

year = "2007",

language = "English",

booktitle = "EPRINTS-BOOK-TITLE",

publisher = "University of Groningen, Johann Bernoulli Institute for Mathematics and Computer Science",

}

TY - CHAP

T1 - Particle Based Image Segmentation with Simulated Annealing

AU - Everts, M.H.

AU - Bekker, H.

AU - Jalba, A.C.

AU - Roerdink, J.B.T.M.

N1 - Relation: http://www.rug.nl/informatica/organisatie/overorganisatie/iwi Rights: University of Groningen. Research Institute for Mathematics and Computing Science (IWI)

PY - 2007

Y1 - 2007

N2 - The Charged Particle Model (CPM) is a physically motivated deformable model for shape recovery and segmentation. It simulates a system of charged particles moving in an electric field generated from the input image, whose positions in the equilibrium state are used for curve or surface reconstruction. As an alternative we propose to use simulated annealing to position these particles and present a fast and simple algorithm that is able to match CPM’s results on images with well defined contours.

AB - The Charged Particle Model (CPM) is a physically motivated deformable model for shape recovery and segmentation. It simulates a system of charged particles moving in an electric field generated from the input image, whose positions in the equilibrium state are used for curve or surface reconstruction. As an alternative we propose to use simulated annealing to position these particles and present a fast and simple algorithm that is able to match CPM’s results on images with well defined contours.

KW - simulated annealing

KW - particle systems

KW - image segmentation

M3 - Chapter

BT - EPRINTS-BOOK-TITLE

PB - University of Groningen, Johann Bernoulli Institute for Mathematics and Computer Science

ER -

Particle Based Image Segmentation with Simulated Annealing

Abstract

Keywords

Access to Document

Handle.net

Fingerprint

Cite this