A hybrid approach to feature segmentation of triangle meshes

Anshuman Razdan, MyungSoo Bae

Research output: Contribution to journalArticle

80 Citations (Scopus)

Abstract

Segmentation of a polygonal mesh is a method of breaking the mesh down into 'meaningful' connected subsets of meshes called regions or features. Several methods have been proposed in the past and they are either vertex based or edge based. The vertex method used here is based on the watershed segmentation scheme which appears prominently in the image segmentation literature and was later applied to the 3D segmentation problem [9,10]. Its main drawback is that it is a vertex based method and no hard boundaries (edges) are created for the features or regions. Edge based methods rely on the dihedral angle between polygon faces to determine if the common edge should be classified as a Feature Edge. However, this method results in many disconnected edges and thereby incomplete feature loops. We propose a hybrid method which takes advantage of both methods mentioned earlier and create regions with complete feature loops. Satisfactory results have been achieved for both CAD parts as well as other laser scanned objects such as bones and ceramic vessels.

Original languageEnglish (US)
Pages (from-to)783-789
Number of pages7
JournalCAD Computer Aided Design
Volume35
Issue number9
DOIs
StatePublished - Aug 2003

Fingerprint

Triangle Mesh
Dihedral angle
Hybrid Approach
Watersheds
Image segmentation
Computer aided design
Bone
Segmentation
Lasers
Mesh
Vertex of a graph
Hybrid Method
Image Segmentation
Vessel
Polygon
Laser
Subset

Keywords

  • Curvature estimation
  • Feature extraction
  • Shape recognition
  • Three-dimensional segmentation
  • Triangle mesh
  • Watershed segmentation

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Industrial and Manufacturing Engineering
  • Geometry and Topology

Cite this

A hybrid approach to feature segmentation of triangle meshes. / Razdan, Anshuman; Bae, MyungSoo.

In: CAD Computer Aided Design, Vol. 35, No. 9, 08.2003, p. 783-789.

Research output: Contribution to journalArticle

Razdan, Anshuman ; Bae, MyungSoo. / A hybrid approach to feature segmentation of triangle meshes. In: CAD Computer Aided Design. 2003 ; Vol. 35, No. 9. pp. 783-789.
@article{30a053f80f0844a8aae665364df7e87d,
title = "A hybrid approach to feature segmentation of triangle meshes",
abstract = "Segmentation of a polygonal mesh is a method of breaking the mesh down into 'meaningful' connected subsets of meshes called regions or features. Several methods have been proposed in the past and they are either vertex based or edge based. The vertex method used here is based on the watershed segmentation scheme which appears prominently in the image segmentation literature and was later applied to the 3D segmentation problem [9,10]. Its main drawback is that it is a vertex based method and no hard boundaries (edges) are created for the features or regions. Edge based methods rely on the dihedral angle between polygon faces to determine if the common edge should be classified as a Feature Edge. However, this method results in many disconnected edges and thereby incomplete feature loops. We propose a hybrid method which takes advantage of both methods mentioned earlier and create regions with complete feature loops. Satisfactory results have been achieved for both CAD parts as well as other laser scanned objects such as bones and ceramic vessels.",
keywords = "Curvature estimation, Feature extraction, Shape recognition, Three-dimensional segmentation, Triangle mesh, Watershed segmentation",
author = "Anshuman Razdan and MyungSoo Bae",
year = "2003",
month = "8",
doi = "10.1016/S0010-4485(02)00101-X",
language = "English (US)",
volume = "35",
pages = "783--789",
journal = "CAD Computer Aided Design",
issn = "0010-4485",
publisher = "Elsevier Limited",
number = "9",

}

TY - JOUR

T1 - A hybrid approach to feature segmentation of triangle meshes

AU - Razdan, Anshuman

AU - Bae, MyungSoo

PY - 2003/8

Y1 - 2003/8

N2 - Segmentation of a polygonal mesh is a method of breaking the mesh down into 'meaningful' connected subsets of meshes called regions or features. Several methods have been proposed in the past and they are either vertex based or edge based. The vertex method used here is based on the watershed segmentation scheme which appears prominently in the image segmentation literature and was later applied to the 3D segmentation problem [9,10]. Its main drawback is that it is a vertex based method and no hard boundaries (edges) are created for the features or regions. Edge based methods rely on the dihedral angle between polygon faces to determine if the common edge should be classified as a Feature Edge. However, this method results in many disconnected edges and thereby incomplete feature loops. We propose a hybrid method which takes advantage of both methods mentioned earlier and create regions with complete feature loops. Satisfactory results have been achieved for both CAD parts as well as other laser scanned objects such as bones and ceramic vessels.

AB - Segmentation of a polygonal mesh is a method of breaking the mesh down into 'meaningful' connected subsets of meshes called regions or features. Several methods have been proposed in the past and they are either vertex based or edge based. The vertex method used here is based on the watershed segmentation scheme which appears prominently in the image segmentation literature and was later applied to the 3D segmentation problem [9,10]. Its main drawback is that it is a vertex based method and no hard boundaries (edges) are created for the features or regions. Edge based methods rely on the dihedral angle between polygon faces to determine if the common edge should be classified as a Feature Edge. However, this method results in many disconnected edges and thereby incomplete feature loops. We propose a hybrid method which takes advantage of both methods mentioned earlier and create regions with complete feature loops. Satisfactory results have been achieved for both CAD parts as well as other laser scanned objects such as bones and ceramic vessels.

KW - Curvature estimation

KW - Feature extraction

KW - Shape recognition

KW - Three-dimensional segmentation

KW - Triangle mesh

KW - Watershed segmentation

UR - http://www.scopus.com/inward/record.url?scp=0037739597&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037739597&partnerID=8YFLogxK

U2 - 10.1016/S0010-4485(02)00101-X

DO - 10.1016/S0010-4485(02)00101-X

M3 - Article

VL - 35

SP - 783

EP - 789

JO - CAD Computer Aided Design

JF - CAD Computer Aided Design

SN - 0010-4485

IS - 9

ER -