Extended isomap for pattern classification

Research output: Contribution to conferencePaper

29 Citations (Scopus)

Abstract

The Isomap method has demonstrated promising results in finding low dimensional manifolds from data points in the high dimensional input space. While classical subspace methods use Euclidean or Manhattan metrics to represent distances between data points and apply Principal Component Analysis to induce linear manifolds, the Isomap method estimates geodesic distances between data points and then uses Multi-Dimensional Scaling to induce low dimensional manifolds. Since the Isomap method is developed based on reconstruction principle, it may not be optimal from the classification viewpoint. In this paper, we present an extended Isomap method that utilizes Fisher Linear Discriminant for pattern classification. Numerous experiments on image data sets show that our extension is more effective than the original Isomap method for pattern classification. Furthermore, the extended Isomap method shows promising results compared with best methods in the face recognition literature.

Original languageEnglish
Pages224-229
Number of pages6
Publication statusPublished - 2002 Dec 1
Event18th National Conference on Artificial Intelligence (AAAI-02), 14th Innovative Applications of Artificial Intelligence Conference (IAAI-02) - Edmonton, Alta., Canada
Duration: 2002 Jul 282002 Aug 1

Conference

Conference18th National Conference on Artificial Intelligence (AAAI-02), 14th Innovative Applications of Artificial Intelligence Conference (IAAI-02)
CountryCanada
CityEdmonton, Alta.
Period02/7/2802/8/1

Fingerprint

Pattern recognition
Face recognition
Principal component analysis
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Yang, M. H. (2002). Extended isomap for pattern classification. 224-229. Paper presented at 18th National Conference on Artificial Intelligence (AAAI-02), 14th Innovative Applications of Artificial Intelligence Conference (IAAI-02), Edmonton, Alta., Canada.
Yang, Ming Hsuan. / Extended isomap for pattern classification. Paper presented at 18th National Conference on Artificial Intelligence (AAAI-02), 14th Innovative Applications of Artificial Intelligence Conference (IAAI-02), Edmonton, Alta., Canada.6 p.
@conference{66d4822e7e014ad28886872b8f433a8a,
title = "Extended isomap for pattern classification",
abstract = "The Isomap method has demonstrated promising results in finding low dimensional manifolds from data points in the high dimensional input space. While classical subspace methods use Euclidean or Manhattan metrics to represent distances between data points and apply Principal Component Analysis to induce linear manifolds, the Isomap method estimates geodesic distances between data points and then uses Multi-Dimensional Scaling to induce low dimensional manifolds. Since the Isomap method is developed based on reconstruction principle, it may not be optimal from the classification viewpoint. In this paper, we present an extended Isomap method that utilizes Fisher Linear Discriminant for pattern classification. Numerous experiments on image data sets show that our extension is more effective than the original Isomap method for pattern classification. Furthermore, the extended Isomap method shows promising results compared with best methods in the face recognition literature.",
author = "Yang, {Ming Hsuan}",
year = "2002",
month = "12",
day = "1",
language = "English",
pages = "224--229",
note = "18th National Conference on Artificial Intelligence (AAAI-02), 14th Innovative Applications of Artificial Intelligence Conference (IAAI-02) ; Conference date: 28-07-2002 Through 01-08-2002",

}

Yang, MH 2002, 'Extended isomap for pattern classification', Paper presented at 18th National Conference on Artificial Intelligence (AAAI-02), 14th Innovative Applications of Artificial Intelligence Conference (IAAI-02), Edmonton, Alta., Canada, 02/7/28 - 02/8/1 pp. 224-229.

Extended isomap for pattern classification. / Yang, Ming Hsuan.

2002. 224-229 Paper presented at 18th National Conference on Artificial Intelligence (AAAI-02), 14th Innovative Applications of Artificial Intelligence Conference (IAAI-02), Edmonton, Alta., Canada.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Extended isomap for pattern classification

AU - Yang, Ming Hsuan

PY - 2002/12/1

Y1 - 2002/12/1

N2 - The Isomap method has demonstrated promising results in finding low dimensional manifolds from data points in the high dimensional input space. While classical subspace methods use Euclidean or Manhattan metrics to represent distances between data points and apply Principal Component Analysis to induce linear manifolds, the Isomap method estimates geodesic distances between data points and then uses Multi-Dimensional Scaling to induce low dimensional manifolds. Since the Isomap method is developed based on reconstruction principle, it may not be optimal from the classification viewpoint. In this paper, we present an extended Isomap method that utilizes Fisher Linear Discriminant for pattern classification. Numerous experiments on image data sets show that our extension is more effective than the original Isomap method for pattern classification. Furthermore, the extended Isomap method shows promising results compared with best methods in the face recognition literature.

AB - The Isomap method has demonstrated promising results in finding low dimensional manifolds from data points in the high dimensional input space. While classical subspace methods use Euclidean or Manhattan metrics to represent distances between data points and apply Principal Component Analysis to induce linear manifolds, the Isomap method estimates geodesic distances between data points and then uses Multi-Dimensional Scaling to induce low dimensional manifolds. Since the Isomap method is developed based on reconstruction principle, it may not be optimal from the classification viewpoint. In this paper, we present an extended Isomap method that utilizes Fisher Linear Discriminant for pattern classification. Numerous experiments on image data sets show that our extension is more effective than the original Isomap method for pattern classification. Furthermore, the extended Isomap method shows promising results compared with best methods in the face recognition literature.

UR - http://www.scopus.com/inward/record.url?scp=0036928021&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036928021&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0036928021

SP - 224

EP - 229

ER -

Yang MH. Extended isomap for pattern classification. 2002. Paper presented at 18th National Conference on Artificial Intelligence (AAAI-02), 14th Innovative Applications of Artificial Intelligence Conference (IAAI-02), Edmonton, Alta., Canada.