Neural net classifier for multi-temporal LANDSAT TM images

Seiichiro Kamata, Eiji Kawaguchi

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The classification of remotely sensed multispectral data using classical statistical methods has been worked on for several decades. Recently there have been many new developments in neural network (NN) research, and many new applications have been studied. It is well known that NN approaches have the ability to classify without assuming a distribution. We have proposed an NN model to combine the spectral and spacial information of a LANDSAT TM image. In this paper, we apply the NN approach with a normalization method to classify multi-temporal LANDSAT TM images in order to investigate the robustness of our approach. From our experiments, we have confirmed that our approach is more effective for the classification of multi-temporal data than the original NN approach and maximum likelihood approach.

Original languageEnglish
Pages (from-to)1295-1300
Number of pages6
JournalIEICE Transactions on Information and Systems
VolumeE78-D
Issue number10
Publication statusPublished - 1995 Oct
Externally publishedYes

Fingerprint

Classifiers
Neural networks
Maximum likelihood
Statistical methods
Experiments

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Information Systems
  • Software

Cite this

Neural net classifier for multi-temporal LANDSAT TM images. / Kamata, Seiichiro; Kawaguchi, Eiji.

In: IEICE Transactions on Information and Systems, Vol. E78-D, No. 10, 10.1995, p. 1295-1300.

Research output: Contribution to journalArticle

@article{a286d3402d4f46ada5e12d2364cfbda5,
title = "Neural net classifier for multi-temporal LANDSAT TM images",
abstract = "The classification of remotely sensed multispectral data using classical statistical methods has been worked on for several decades. Recently there have been many new developments in neural network (NN) research, and many new applications have been studied. It is well known that NN approaches have the ability to classify without assuming a distribution. We have proposed an NN model to combine the spectral and spacial information of a LANDSAT TM image. In this paper, we apply the NN approach with a normalization method to classify multi-temporal LANDSAT TM images in order to investigate the robustness of our approach. From our experiments, we have confirmed that our approach is more effective for the classification of multi-temporal data than the original NN approach and maximum likelihood approach.",
author = "Seiichiro Kamata and Eiji Kawaguchi",
year = "1995",
month = "10",
language = "English",
volume = "E78-D",
pages = "1295--1300",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "10",

}

TY - JOUR

T1 - Neural net classifier for multi-temporal LANDSAT TM images

AU - Kamata, Seiichiro

AU - Kawaguchi, Eiji

PY - 1995/10

Y1 - 1995/10

N2 - The classification of remotely sensed multispectral data using classical statistical methods has been worked on for several decades. Recently there have been many new developments in neural network (NN) research, and many new applications have been studied. It is well known that NN approaches have the ability to classify without assuming a distribution. We have proposed an NN model to combine the spectral and spacial information of a LANDSAT TM image. In this paper, we apply the NN approach with a normalization method to classify multi-temporal LANDSAT TM images in order to investigate the robustness of our approach. From our experiments, we have confirmed that our approach is more effective for the classification of multi-temporal data than the original NN approach and maximum likelihood approach.

AB - The classification of remotely sensed multispectral data using classical statistical methods has been worked on for several decades. Recently there have been many new developments in neural network (NN) research, and many new applications have been studied. It is well known that NN approaches have the ability to classify without assuming a distribution. We have proposed an NN model to combine the spectral and spacial information of a LANDSAT TM image. In this paper, we apply the NN approach with a normalization method to classify multi-temporal LANDSAT TM images in order to investigate the robustness of our approach. From our experiments, we have confirmed that our approach is more effective for the classification of multi-temporal data than the original NN approach and maximum likelihood approach.

UR - http://www.scopus.com/inward/record.url?scp=0029389323&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029389323&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0029389323

VL - E78-D

SP - 1295

EP - 1300

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 10

ER -