Genetic algorithms for 3D reconstruction with supershapes

S. Voisin, M. A. Abidi, Sebti Foufou, F. Truchetet

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Supershape model is a recent primitive that represents numerous 3D shapes with several symmetry axes. The main interest of this model is its capability to reconstruct more complex shape than superquadric model with only one implicit equation. In this paper we propose a genetic algorithms to reconstruct a point cloud using those primitives. We used the pseudo-Euclidean distance to introduce a threshold to handle real data imperfection and speed up the process. Simulations using our proposed fitness functions and a fitness function based on inside-outside function show that our fitness function based on the pseudo-Euclidean distance performs better.

Original languageEnglish (US)
Title of host publication2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings
PublisherIEEE Computer Society
Pages529-532
Number of pages4
ISBN (Print)9781424456543
DOIs
StatePublished - Jan 1 2009
Event2009 IEEE International Conference on Image Processing, ICIP 2009 - Cairo, Egypt
Duration: Nov 7 2009Nov 10 2009

Other

Other2009 IEEE International Conference on Image Processing, ICIP 2009
CountryEgypt
CityCairo
Period11/7/0911/10/09

Fingerprint

Genetic algorithms
Defects

Keywords

  • 3D reconstruction
  • Genetic algorithms
  • Pseudo-Euclidean distance
  • Supershapes

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Voisin, S., Abidi, M. A., Foufou, S., & Truchetet, F. (2009). Genetic algorithms for 3D reconstruction with supershapes. In 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings (pp. 529-532). [5413905] IEEE Computer Society. https://doi.org/10.1109/ICIP.2009.5413905

Genetic algorithms for 3D reconstruction with supershapes. / Voisin, S.; Abidi, M. A.; Foufou, Sebti; Truchetet, F.

2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings. IEEE Computer Society, 2009. p. 529-532 5413905.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Voisin, S, Abidi, MA, Foufou, S & Truchetet, F 2009, Genetic algorithms for 3D reconstruction with supershapes. in 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings., 5413905, IEEE Computer Society, pp. 529-532, 2009 IEEE International Conference on Image Processing, ICIP 2009, Cairo, Egypt, 11/7/09. https://doi.org/10.1109/ICIP.2009.5413905
Voisin S, Abidi MA, Foufou S, Truchetet F. Genetic algorithms for 3D reconstruction with supershapes. In 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings. IEEE Computer Society. 2009. p. 529-532. 5413905 https://doi.org/10.1109/ICIP.2009.5413905
Voisin, S. ; Abidi, M. A. ; Foufou, Sebti ; Truchetet, F. / Genetic algorithms for 3D reconstruction with supershapes. 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings. IEEE Computer Society, 2009. pp. 529-532
@inproceedings{625a6fea3a434dc0be7e0b2d2f249440,
title = "Genetic algorithms for 3D reconstruction with supershapes",
abstract = "Supershape model is a recent primitive that represents numerous 3D shapes with several symmetry axes. The main interest of this model is its capability to reconstruct more complex shape than superquadric model with only one implicit equation. In this paper we propose a genetic algorithms to reconstruct a point cloud using those primitives. We used the pseudo-Euclidean distance to introduce a threshold to handle real data imperfection and speed up the process. Simulations using our proposed fitness functions and a fitness function based on inside-outside function show that our fitness function based on the pseudo-Euclidean distance performs better.",
keywords = "3D reconstruction, Genetic algorithms, Pseudo-Euclidean distance, Supershapes",
author = "S. Voisin and Abidi, {M. A.} and Sebti Foufou and F. Truchetet",
year = "2009",
month = "1",
day = "1",
doi = "10.1109/ICIP.2009.5413905",
language = "English (US)",
isbn = "9781424456543",
pages = "529--532",
booktitle = "2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Genetic algorithms for 3D reconstruction with supershapes

AU - Voisin, S.

AU - Abidi, M. A.

AU - Foufou, Sebti

AU - Truchetet, F.

PY - 2009/1/1

Y1 - 2009/1/1

N2 - Supershape model is a recent primitive that represents numerous 3D shapes with several symmetry axes. The main interest of this model is its capability to reconstruct more complex shape than superquadric model with only one implicit equation. In this paper we propose a genetic algorithms to reconstruct a point cloud using those primitives. We used the pseudo-Euclidean distance to introduce a threshold to handle real data imperfection and speed up the process. Simulations using our proposed fitness functions and a fitness function based on inside-outside function show that our fitness function based on the pseudo-Euclidean distance performs better.

AB - Supershape model is a recent primitive that represents numerous 3D shapes with several symmetry axes. The main interest of this model is its capability to reconstruct more complex shape than superquadric model with only one implicit equation. In this paper we propose a genetic algorithms to reconstruct a point cloud using those primitives. We used the pseudo-Euclidean distance to introduce a threshold to handle real data imperfection and speed up the process. Simulations using our proposed fitness functions and a fitness function based on inside-outside function show that our fitness function based on the pseudo-Euclidean distance performs better.

KW - 3D reconstruction

KW - Genetic algorithms

KW - Pseudo-Euclidean distance

KW - Supershapes

UR - http://www.scopus.com/inward/record.url?scp=77951964943&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951964943&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2009.5413905

DO - 10.1109/ICIP.2009.5413905

M3 - Conference contribution

AN - SCOPUS:77951964943

SN - 9781424456543

SP - 529

EP - 532

BT - 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings

PB - IEEE Computer Society

ER -