Multi-phase image segmentation with the adaptive deformable mesh

Tuan T. Nguyen*, Vedrana A. Dahl, J. Andreas Bærentzen

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

This paper proposes a method for image segmentation using a deformable triangle mesh in the image domain. We define a piecewise constant function by labeling the mesh triangles with different phases, each representing a segment of an image. Our method finds the optimal mesh configuration and triangle labeling that minimize the piecewise constant Mumford-Shah functional. Contributions of this paper include a force model that moves mesh vertices towards the solution, and an adaptivity model that further adapts the mesh by introducing or removing vertices. The results demonstrate the advantages of our method over traditional methods like snakes and level set. Our approach supports multi-phase segmentation incurring no particular overhead. Furthermore, the use of an adaptive mesh facilitates accurate segmentation with a very compact representation. The biggest challenge of deformable meshes, changes to the topology of the segments, is handled by employing Deformable Simplical Complex (DSC), a method for explicit interface tracking.

Original languageEnglish
JournalPattern Recognition Letters
Volume117
Pages (from-to)97-103
Number of pages7
ISSN0167-8655
DOIs
Publication statusPublished - 2019

Keywords

  • Active contour
  • Adaptive mesh
  • Deformable model
  • Explicit mesh
  • Multi-phase
  • Mumford-Shah
  • Triangle mesh

Cite this

@article{99dbe4c3ebb742599775d4b4097f2abe,
title = "Multi-phase image segmentation with the adaptive deformable mesh",
abstract = "This paper proposes a method for image segmentation using a deformable triangle mesh in the image domain. We define a piecewise constant function by labeling the mesh triangles with different phases, each representing a segment of an image. Our method finds the optimal mesh configuration and triangle labeling that minimize the piecewise constant Mumford-Shah functional. Contributions of this paper include a force model that moves mesh vertices towards the solution, and an adaptivity model that further adapts the mesh by introducing or removing vertices. The results demonstrate the advantages of our method over traditional methods like snakes and level set. Our approach supports multi-phase segmentation incurring no particular overhead. Furthermore, the use of an adaptive mesh facilitates accurate segmentation with a very compact representation. The biggest challenge of deformable meshes, changes to the topology of the segments, is handled by employing Deformable Simplical Complex (DSC), a method for explicit interface tracking.",
keywords = "Active contour, Adaptive mesh, Deformable model, Explicit mesh, Multi-phase, Mumford-Shah, Triangle mesh",
author = "Nguyen, {Tuan T.} and Dahl, {Vedrana A.} and B{\ae}rentzen, {J. Andreas}",
year = "2019",
doi = "10.1016/j.patrec.2018.12.009",
language = "English",
volume = "117",
pages = "97--103",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",

}

Multi-phase image segmentation with the adaptive deformable mesh. / Nguyen, Tuan T.; Dahl, Vedrana A.; Bærentzen, J. Andreas.

In: Pattern Recognition Letters, Vol. 117, 2019, p. 97-103.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Multi-phase image segmentation with the adaptive deformable mesh

AU - Nguyen, Tuan T.

AU - Dahl, Vedrana A.

AU - Bærentzen, J. Andreas

PY - 2019

Y1 - 2019

N2 - This paper proposes a method for image segmentation using a deformable triangle mesh in the image domain. We define a piecewise constant function by labeling the mesh triangles with different phases, each representing a segment of an image. Our method finds the optimal mesh configuration and triangle labeling that minimize the piecewise constant Mumford-Shah functional. Contributions of this paper include a force model that moves mesh vertices towards the solution, and an adaptivity model that further adapts the mesh by introducing or removing vertices. The results demonstrate the advantages of our method over traditional methods like snakes and level set. Our approach supports multi-phase segmentation incurring no particular overhead. Furthermore, the use of an adaptive mesh facilitates accurate segmentation with a very compact representation. The biggest challenge of deformable meshes, changes to the topology of the segments, is handled by employing Deformable Simplical Complex (DSC), a method for explicit interface tracking.

AB - This paper proposes a method for image segmentation using a deformable triangle mesh in the image domain. We define a piecewise constant function by labeling the mesh triangles with different phases, each representing a segment of an image. Our method finds the optimal mesh configuration and triangle labeling that minimize the piecewise constant Mumford-Shah functional. Contributions of this paper include a force model that moves mesh vertices towards the solution, and an adaptivity model that further adapts the mesh by introducing or removing vertices. The results demonstrate the advantages of our method over traditional methods like snakes and level set. Our approach supports multi-phase segmentation incurring no particular overhead. Furthermore, the use of an adaptive mesh facilitates accurate segmentation with a very compact representation. The biggest challenge of deformable meshes, changes to the topology of the segments, is handled by employing Deformable Simplical Complex (DSC), a method for explicit interface tracking.

KW - Active contour

KW - Adaptive mesh

KW - Deformable model

KW - Explicit mesh

KW - Multi-phase

KW - Mumford-Shah

KW - Triangle mesh

U2 - 10.1016/j.patrec.2018.12.009

DO - 10.1016/j.patrec.2018.12.009

M3 - Journal article

VL - 117

SP - 97

EP - 103

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

ER -