Strategies of multi-view and multi-matching for 3D object recognition

Sei-Wang Chen, Anil K. Jain

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

A multi-view representation scheme and a multi-matching strategy for 3D object recognition are described; 3D objects are represented in terms of their 2D appearances so that 2D techniques can be applied to 3D recognition. Appearances of objects in the representation scheme are further organized in a hierarchical manner so that the matching process can reduce its search space by examining only the optimal view at every level of the representation scheme. In our multi-matching strategy, the matching module is composed of four components: point matcher, string matcher, vector matcher, and chamfer matcher. Each matcher is associated with a termination rule so that impossible views can be rejected at the early stages of the matching process. Experimental results reveal that the proposed strategies are feasible for 3D object recognition.

Original languageEnglish
Pages (from-to)121-130
Number of pages10
JournalComputer Vision and Image Understanding
Volume57
Issue number1
DOIs
Publication statusPublished - 1993 Jan 1

Fingerprint

Object recognition

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

Strategies of multi-view and multi-matching for 3D object recognition. / Chen, Sei-Wang; Jain, Anil K.

In: Computer Vision and Image Understanding, Vol. 57, No. 1, 01.01.1993, p. 121-130.

Research output: Contribution to journalArticle

@article{df8c12d06e414efaad4254cb563bb129,
title = "Strategies of multi-view and multi-matching for 3D object recognition",
abstract = "A multi-view representation scheme and a multi-matching strategy for 3D object recognition are described; 3D objects are represented in terms of their 2D appearances so that 2D techniques can be applied to 3D recognition. Appearances of objects in the representation scheme are further organized in a hierarchical manner so that the matching process can reduce its search space by examining only the optimal view at every level of the representation scheme. In our multi-matching strategy, the matching module is composed of four components: point matcher, string matcher, vector matcher, and chamfer matcher. Each matcher is associated with a termination rule so that impossible views can be rejected at the early stages of the matching process. Experimental results reveal that the proposed strategies are feasible for 3D object recognition.",
author = "Sei-Wang Chen and Jain, {Anil K.}",
year = "1993",
month = "1",
day = "1",
doi = "10.1006/cviu.1993.1008",
language = "English",
volume = "57",
pages = "121--130",
journal = "Computer Vision and Image Understanding",
issn = "1077-3142",
publisher = "Academic Press Inc.",
number = "1",

}

TY - JOUR

T1 - Strategies of multi-view and multi-matching for 3D object recognition

AU - Chen, Sei-Wang

AU - Jain, Anil K.

PY - 1993/1/1

Y1 - 1993/1/1

N2 - A multi-view representation scheme and a multi-matching strategy for 3D object recognition are described; 3D objects are represented in terms of their 2D appearances so that 2D techniques can be applied to 3D recognition. Appearances of objects in the representation scheme are further organized in a hierarchical manner so that the matching process can reduce its search space by examining only the optimal view at every level of the representation scheme. In our multi-matching strategy, the matching module is composed of four components: point matcher, string matcher, vector matcher, and chamfer matcher. Each matcher is associated with a termination rule so that impossible views can be rejected at the early stages of the matching process. Experimental results reveal that the proposed strategies are feasible for 3D object recognition.

AB - A multi-view representation scheme and a multi-matching strategy for 3D object recognition are described; 3D objects are represented in terms of their 2D appearances so that 2D techniques can be applied to 3D recognition. Appearances of objects in the representation scheme are further organized in a hierarchical manner so that the matching process can reduce its search space by examining only the optimal view at every level of the representation scheme. In our multi-matching strategy, the matching module is composed of four components: point matcher, string matcher, vector matcher, and chamfer matcher. Each matcher is associated with a termination rule so that impossible views can be rejected at the early stages of the matching process. Experimental results reveal that the proposed strategies are feasible for 3D object recognition.

UR - http://www.scopus.com/inward/record.url?scp=9344252121&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=9344252121&partnerID=8YFLogxK

U2 - 10.1006/cviu.1993.1008

DO - 10.1006/cviu.1993.1008

M3 - Article

AN - SCOPUS:9344252121

VL - 57

SP - 121

EP - 130

JO - Computer Vision and Image Understanding

JF - Computer Vision and Image Understanding

SN - 1077-3142

IS - 1

ER -