Minimal surfaces based object segmentation

Vincent Caselles; Ron Kimmel; Guillermo Sapiro; Catalina Sbert

doi:10.1109/34.588023

Minimal surfaces based object segmentation

Vincent Caselles, Ron Kimmel, Guillermo Sapiro, Catalina Sbert

Research output: Contribution to journal › Article › peer-review

160 Scopus citations

Abstract

A geometric approach for 3D object segmentation and representation is presented. The segmentation is obtained by deformable surfaces moving towards the objects to be detected in the 3D image. The model is based on curvature motion and the computation of surfaces with minimal areas better known as minimal surfaces. The space where the surfaces are computed is induced from the 3D image (volumetric data) in which the objects are to be detected. The model links between classical deformable surfaces obtained via energy minimization and intrinsic ones derived from curvature based flows. The new approach is stable robust and automatically handles changes in the surface topology during the deformation.

Original language	English (US)
Pages (from-to)	394-398
Number of pages	5
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	19
Issue number	4
DOIs	https://doi.org/10.1109/34.588023
State	Published - 1997
Externally published	Yes

All Science Journal Classification (ASJC) codes

Software
Computer Vision and Pattern Recognition
Computational Theory and Mathematics
Artificial Intelligence
Applied Mathematics

Keywords

3d segmentation
Deformable models
Mean curvature motion
Medical images
Minimal surfaces

Access to Document

10.1109/34.588023

Cite this

@article{574cc68a1d264010b8bae2e5ccb37c1a,

title = "Minimal surfaces based object segmentation",

abstract = "A geometric approach for 3D object segmentation and representation is presented. The segmentation is obtained by deformable surfaces moving towards the objects to be detected in the 3D image. The model is based on curvature motion and the computation of surfaces with minimal areas better known as minimal surfaces. The space where the surfaces are computed is induced from the 3D image (volumetric data) in which the objects are to be detected. The model links between classical deformable surfaces obtained via energy minimization and intrinsic ones derived from curvature based flows. The new approach is stable robust and automatically handles changes in the surface topology during the deformation.",

keywords = "3d segmentation, Deformable models, Mean curvature motion, Medical images, Minimal surfaces",

author = "Vincent Caselles and Ron Kimmel and Guillermo Sapiro and Catalina Sbert",

year = "1997",

doi = "10.1109/34.588023",

language = "English (US)",

volume = "19",

pages = "394--398",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "IEEE Computer Society",

number = "4",

}

TY - JOUR

T1 - Minimal surfaces based object segmentation

AU - Caselles, Vincent

AU - Kimmel, Ron

AU - Sapiro, Guillermo

AU - Sbert, Catalina

PY - 1997

Y1 - 1997

N2 - A geometric approach for 3D object segmentation and representation is presented. The segmentation is obtained by deformable surfaces moving towards the objects to be detected in the 3D image. The model is based on curvature motion and the computation of surfaces with minimal areas better known as minimal surfaces. The space where the surfaces are computed is induced from the 3D image (volumetric data) in which the objects are to be detected. The model links between classical deformable surfaces obtained via energy minimization and intrinsic ones derived from curvature based flows. The new approach is stable robust and automatically handles changes in the surface topology during the deformation.

AB - A geometric approach for 3D object segmentation and representation is presented. The segmentation is obtained by deformable surfaces moving towards the objects to be detected in the 3D image. The model is based on curvature motion and the computation of surfaces with minimal areas better known as minimal surfaces. The space where the surfaces are computed is induced from the 3D image (volumetric data) in which the objects are to be detected. The model links between classical deformable surfaces obtained via energy minimization and intrinsic ones derived from curvature based flows. The new approach is stable robust and automatically handles changes in the surface topology during the deformation.

KW - 3d segmentation

KW - Deformable models

KW - Mean curvature motion

KW - Medical images

KW - Minimal surfaces

UR - http://www.scopus.com/inward/record.url?scp=0031122564&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031122564&partnerID=8YFLogxK

U2 - 10.1109/34.588023

DO - 10.1109/34.588023

M3 - Article

AN - SCOPUS:0031122564

SN - 0162-8828

VL - 19

SP - 394

EP - 398

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 4

ER -

Minimal surfaces based object segmentation

Abstract

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this