A neural network classifier for LANDSAT image data

Seiichiro Kamata, Richard O. Eason, Arnulfo Perez, Eiji Kawaguchi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

There have been many new developments in neural network (NN) research, and many new applications have been studied. The classification of remotely sensed multispectral data using classical statistical methods has been worked on for several decades. Among the multispectral data, we concentrate on the LANDSAT-5 Thematic Mapper (TM) image data which has been available since 1984-Using the classical maximum likelihood approach, a category is modeled as a multivariate normal distribution; however, the distribution for LANDSAT images is unknown. It is well known that NN approaches have the ability to classify without assuming a distribution. We apply the NN approach to the classification of LANDSAT TM images in order to investigate the robustness of this approach for multi temporal data classification. We confirmed that the NN approach is effective for the classification even if the test data is taken at the different time.

Original languageEnglish
Title of host publicationConference B
Subtitle of host publicationPattern Recognition Methodology and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages573-576
Number of pages4
Volume2
ISBN (Print)0818629150
DOIs
Publication statusPublished - 1992 Jan 1
Externally publishedYes
Event11th IAPR International Conference on Pattern Recognition, IAPR 1992 - The Hague, Netherlands
Duration: 1992 Aug 301992 Sep 3

Other

Other11th IAPR International Conference on Pattern Recognition, IAPR 1992
CountryNetherlands
CityThe Hague
Period92/8/3092/9/3

Fingerprint

Classifiers
Neural networks
Normal distribution
Maximum likelihood
Statistical methods

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Kamata, S., Eason, R. O., Perez, A., & Kawaguchi, E. (1992). A neural network classifier for LANDSAT image data. In Conference B: Pattern Recognition Methodology and Systems (Vol. 2, pp. 573-576). [201843] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.1992.201843

A neural network classifier for LANDSAT image data. / Kamata, Seiichiro; Eason, Richard O.; Perez, Arnulfo; Kawaguchi, Eiji.

Conference B: Pattern Recognition Methodology and Systems. Vol. 2 Institute of Electrical and Electronics Engineers Inc., 1992. p. 573-576 201843.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kamata, S, Eason, RO, Perez, A & Kawaguchi, E 1992, A neural network classifier for LANDSAT image data. in Conference B: Pattern Recognition Methodology and Systems. vol. 2, 201843, Institute of Electrical and Electronics Engineers Inc., pp. 573-576, 11th IAPR International Conference on Pattern Recognition, IAPR 1992, The Hague, Netherlands, 92/8/30. https://doi.org/10.1109/ICPR.1992.201843
Kamata S, Eason RO, Perez A, Kawaguchi E. A neural network classifier for LANDSAT image data. In Conference B: Pattern Recognition Methodology and Systems. Vol. 2. Institute of Electrical and Electronics Engineers Inc. 1992. p. 573-576. 201843 https://doi.org/10.1109/ICPR.1992.201843
Kamata, Seiichiro ; Eason, Richard O. ; Perez, Arnulfo ; Kawaguchi, Eiji. / A neural network classifier for LANDSAT image data. Conference B: Pattern Recognition Methodology and Systems. Vol. 2 Institute of Electrical and Electronics Engineers Inc., 1992. pp. 573-576
@inproceedings{52d173b9aedd46c0b480677d6d40282b,
title = "A neural network classifier for LANDSAT image data",
abstract = "There have been many new developments in neural network (NN) research, and many new applications have been studied. The classification of remotely sensed multispectral data using classical statistical methods has been worked on for several decades. Among the multispectral data, we concentrate on the LANDSAT-5 Thematic Mapper (TM) image data which has been available since 1984-Using the classical maximum likelihood approach, a category is modeled as a multivariate normal distribution; however, the distribution for LANDSAT images is unknown. It is well known that NN approaches have the ability to classify without assuming a distribution. We apply the NN approach to the classification of LANDSAT TM images in order to investigate the robustness of this approach for multi temporal data classification. We confirmed that the NN approach is effective for the classification even if the test data is taken at the different time.",
author = "Seiichiro Kamata and Eason, {Richard O.} and Arnulfo Perez and Eiji Kawaguchi",
year = "1992",
month = "1",
day = "1",
doi = "10.1109/ICPR.1992.201843",
language = "English",
isbn = "0818629150",
volume = "2",
pages = "573--576",
booktitle = "Conference B",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A neural network classifier for LANDSAT image data

AU - Kamata, Seiichiro

AU - Eason, Richard O.

AU - Perez, Arnulfo

AU - Kawaguchi, Eiji

PY - 1992/1/1

Y1 - 1992/1/1

N2 - There have been many new developments in neural network (NN) research, and many new applications have been studied. The classification of remotely sensed multispectral data using classical statistical methods has been worked on for several decades. Among the multispectral data, we concentrate on the LANDSAT-5 Thematic Mapper (TM) image data which has been available since 1984-Using the classical maximum likelihood approach, a category is modeled as a multivariate normal distribution; however, the distribution for LANDSAT images is unknown. It is well known that NN approaches have the ability to classify without assuming a distribution. We apply the NN approach to the classification of LANDSAT TM images in order to investigate the robustness of this approach for multi temporal data classification. We confirmed that the NN approach is effective for the classification even if the test data is taken at the different time.

AB - There have been many new developments in neural network (NN) research, and many new applications have been studied. The classification of remotely sensed multispectral data using classical statistical methods has been worked on for several decades. Among the multispectral data, we concentrate on the LANDSAT-5 Thematic Mapper (TM) image data which has been available since 1984-Using the classical maximum likelihood approach, a category is modeled as a multivariate normal distribution; however, the distribution for LANDSAT images is unknown. It is well known that NN approaches have the ability to classify without assuming a distribution. We apply the NN approach to the classification of LANDSAT TM images in order to investigate the robustness of this approach for multi temporal data classification. We confirmed that the NN approach is effective for the classification even if the test data is taken at the different time.

UR - http://www.scopus.com/inward/record.url?scp=0041312315&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0041312315&partnerID=8YFLogxK

U2 - 10.1109/ICPR.1992.201843

DO - 10.1109/ICPR.1992.201843

M3 - Conference contribution

SN - 0818629150

VL - 2

SP - 573

EP - 576

BT - Conference B

PB - Institute of Electrical and Electronics Engineers Inc.

ER -