Fast multistage Gaussian maximum likelihood classifier

Chulhee Lee, David A. Landgrebe

Research output: Contribution to conferencePaper

Abstract

The authors propose a multistage classification algorithm based on the Gaussian maximum-likelihood (ML) procedure. A discriminant function is calculated for classes at each stage, and the classes whose discriminant function values are less than a threshold are truncated. The algorithm reduces processing time substantially without losing any significant accuracy. The computing time can be reduced by a factor of 3-7 using the proposed multistage classifiers when the Gaussian ML classifier is to be used. Therefore, after features which depend on an accuracy requirement have been selected, the processing time can be reduced substantially without losing any significant accuracy by employing the multistage classifiers.

Original languageEnglish
Pages349-352
Number of pages4
Publication statusPublished - 1990 Dec 1
Event10th Annual International Geoscience and Remote Sensing Symposium - IGARSS '90 - College Park, MD, USA
Duration: 1990 May 201990 May 20

Other

Other10th Annual International Geoscience and Remote Sensing Symposium - IGARSS '90
CityCollege Park, MD, USA
Period90/5/2090/5/20

Fingerprint

Maximum likelihood
Classifiers
Processing

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Earth and Planetary Sciences(all)

Cite this

Lee, C., & Landgrebe, D. A. (1990). Fast multistage Gaussian maximum likelihood classifier. 349-352. Paper presented at 10th Annual International Geoscience and Remote Sensing Symposium - IGARSS '90, College Park, MD, USA, .
Lee, Chulhee ; Landgrebe, David A. / Fast multistage Gaussian maximum likelihood classifier. Paper presented at 10th Annual International Geoscience and Remote Sensing Symposium - IGARSS '90, College Park, MD, USA, .4 p.
@conference{0cd9183aefc94e838bb8e7229cd88951,
title = "Fast multistage Gaussian maximum likelihood classifier",
abstract = "The authors propose a multistage classification algorithm based on the Gaussian maximum-likelihood (ML) procedure. A discriminant function is calculated for classes at each stage, and the classes whose discriminant function values are less than a threshold are truncated. The algorithm reduces processing time substantially without losing any significant accuracy. The computing time can be reduced by a factor of 3-7 using the proposed multistage classifiers when the Gaussian ML classifier is to be used. Therefore, after features which depend on an accuracy requirement have been selected, the processing time can be reduced substantially without losing any significant accuracy by employing the multistage classifiers.",
author = "Chulhee Lee and Landgrebe, {David A.}",
year = "1990",
month = "12",
day = "1",
language = "English",
pages = "349--352",
note = "10th Annual International Geoscience and Remote Sensing Symposium - IGARSS '90 ; Conference date: 20-05-1990 Through 20-05-1990",

}

Lee, C & Landgrebe, DA 1990, 'Fast multistage Gaussian maximum likelihood classifier', Paper presented at 10th Annual International Geoscience and Remote Sensing Symposium - IGARSS '90, College Park, MD, USA, 90/5/20 - 90/5/20 pp. 349-352.

Fast multistage Gaussian maximum likelihood classifier. / Lee, Chulhee; Landgrebe, David A.

1990. 349-352 Paper presented at 10th Annual International Geoscience and Remote Sensing Symposium - IGARSS '90, College Park, MD, USA, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Fast multistage Gaussian maximum likelihood classifier

AU - Lee, Chulhee

AU - Landgrebe, David A.

PY - 1990/12/1

Y1 - 1990/12/1

N2 - The authors propose a multistage classification algorithm based on the Gaussian maximum-likelihood (ML) procedure. A discriminant function is calculated for classes at each stage, and the classes whose discriminant function values are less than a threshold are truncated. The algorithm reduces processing time substantially without losing any significant accuracy. The computing time can be reduced by a factor of 3-7 using the proposed multistage classifiers when the Gaussian ML classifier is to be used. Therefore, after features which depend on an accuracy requirement have been selected, the processing time can be reduced substantially without losing any significant accuracy by employing the multistage classifiers.

AB - The authors propose a multistage classification algorithm based on the Gaussian maximum-likelihood (ML) procedure. A discriminant function is calculated for classes at each stage, and the classes whose discriminant function values are less than a threshold are truncated. The algorithm reduces processing time substantially without losing any significant accuracy. The computing time can be reduced by a factor of 3-7 using the proposed multistage classifiers when the Gaussian ML classifier is to be used. Therefore, after features which depend on an accuracy requirement have been selected, the processing time can be reduced substantially without losing any significant accuracy by employing the multistage classifiers.

UR - http://www.scopus.com/inward/record.url?scp=0025556157&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025556157&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0025556157

SP - 349

EP - 352

ER -

Lee C, Landgrebe DA. Fast multistage Gaussian maximum likelihood classifier. 1990. Paper presented at 10th Annual International Geoscience and Remote Sensing Symposium - IGARSS '90, College Park, MD, USA, .