The use of maximum curvature points for the recognition of partially occluded objects

Min Hong Han, Dong Sik Jang

Research output: Contribution to journalArticle

82 Citations (Scopus)

Abstract

A graph-theoretic optimization method is used to recognize partially occluded objects from a 2-D image through the use of maximal cliques and a weight matching algorithm. The vertices of an occluded object image with high curvature values are classified by the objects which are hypothesized to be involved in the occlusion. A heuristic method is also developed to further improve the computational speed. A few typical examples are given to illustrate the accuracy of the optimization model as well as the simplicity of the companion heuristic method.

Original languageEnglish
Pages (from-to)21-33
Number of pages13
JournalPattern Recognition
Volume23
Issue number1-2
DOIs
Publication statusPublished - 1990 Jan 1
Externally publishedYes

Fingerprint

Heuristic methods

Keywords

  • Clique
  • Occlusion
  • Polygonization
  • Weight matching

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

The use of maximum curvature points for the recognition of partially occluded objects. / Han, Min Hong; Jang, Dong Sik.

In: Pattern Recognition, Vol. 23, No. 1-2, 01.01.1990, p. 21-33.

Research output: Contribution to journalArticle

@article{c0e47bb1546840289b05335506f17bac,
title = "The use of maximum curvature points for the recognition of partially occluded objects",
abstract = "A graph-theoretic optimization method is used to recognize partially occluded objects from a 2-D image through the use of maximal cliques and a weight matching algorithm. The vertices of an occluded object image with high curvature values are classified by the objects which are hypothesized to be involved in the occlusion. A heuristic method is also developed to further improve the computational speed. A few typical examples are given to illustrate the accuracy of the optimization model as well as the simplicity of the companion heuristic method.",
keywords = "Clique, Occlusion, Polygonization, Weight matching",
author = "Han, {Min Hong} and Jang, {Dong Sik}",
year = "1990",
month = "1",
day = "1",
doi = "10.1016/0031-3203(90)90046-N",
language = "English",
volume = "23",
pages = "21--33",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "1-2",

}

TY - JOUR

T1 - The use of maximum curvature points for the recognition of partially occluded objects

AU - Han, Min Hong

AU - Jang, Dong Sik

PY - 1990/1/1

Y1 - 1990/1/1

N2 - A graph-theoretic optimization method is used to recognize partially occluded objects from a 2-D image through the use of maximal cliques and a weight matching algorithm. The vertices of an occluded object image with high curvature values are classified by the objects which are hypothesized to be involved in the occlusion. A heuristic method is also developed to further improve the computational speed. A few typical examples are given to illustrate the accuracy of the optimization model as well as the simplicity of the companion heuristic method.

AB - A graph-theoretic optimization method is used to recognize partially occluded objects from a 2-D image through the use of maximal cliques and a weight matching algorithm. The vertices of an occluded object image with high curvature values are classified by the objects which are hypothesized to be involved in the occlusion. A heuristic method is also developed to further improve the computational speed. A few typical examples are given to illustrate the accuracy of the optimization model as well as the simplicity of the companion heuristic method.

KW - Clique

KW - Occlusion

KW - Polygonization

KW - Weight matching

UR - http://www.scopus.com/inward/record.url?scp=0025671725&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025671725&partnerID=8YFLogxK

U2 - 10.1016/0031-3203(90)90046-N

DO - 10.1016/0031-3203(90)90046-N

M3 - Article

AN - SCOPUS:0025671725

VL - 23

SP - 21

EP - 33

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 1-2

ER -