Interactive system for classifying multispectral images using a Hilbert curve

Michiharu Niimi, Seiichiro Kamata, Eiji Kawaguchi

研究成果: Conference contribution

抄録

There are several techniques for analyzing multispectral images. In general, those are performed by linear transformation methods. In this paper, we present a new interactive method for classifying multispectral images using a Hilbert curve which is a one-to-one mapping from N- dimensional space to one dimensional space and preserves the neighborhood as much as possible. The merit of our system is that the user can extract clusters without computing any distance in N- dimensional space, and analyze multidimensional data from gross data distribution to fine data distribution hierarchically. In the experiments using LANDSAT TM data, it is confirmed that the user can get the real time response from the system after once making the data tables, and understand distribution of data that correspond to categories in feature space.

元の言語English
ホスト出版物のタイトルProceedings of SPIE - The International Society for Optical Engineering
出版場所Bellingham, WA, United States
出版者Society of Photo-Optical Instrumentation Engineers
ページ1647-1655
ページ数9
2501
エディション3/-
ISBN(印刷物)0819418587
出版物ステータスPublished - 1995
外部発表Yes
イベントVisual Communications and Image Processing '95 - Taipei, Taiwan
継続期間: 1995 5 241995 5 26

Other

OtherVisual Communications and Image Processing '95
Taipei, Taiwan
期間95/5/2495/5/26

Fingerprint

Cluster computing
Linear transformations
classifying
curves
Experiments
linear transformations
time response

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

これを引用

Niimi, M., Kamata, S., & Kawaguchi, E. (1995). Interactive system for classifying multispectral images using a Hilbert curve. : Proceedings of SPIE - The International Society for Optical Engineering (3/- 版, 巻 2501 , pp. 1647-1655). Bellingham, WA, United States: Society of Photo-Optical Instrumentation Engineers.

Interactive system for classifying multispectral images using a Hilbert curve. / Niimi, Michiharu; Kamata, Seiichiro; Kawaguchi, Eiji.

Proceedings of SPIE - The International Society for Optical Engineering. 巻 2501 3/-. 編 Bellingham, WA, United States : Society of Photo-Optical Instrumentation Engineers, 1995. p. 1647-1655.

研究成果: Conference contribution

Niimi, M, Kamata, S & Kawaguchi, E 1995, Interactive system for classifying multispectral images using a Hilbert curve. : Proceedings of SPIE - The International Society for Optical Engineering. 3/- Edn, 巻. 2501 , Society of Photo-Optical Instrumentation Engineers, Bellingham, WA, United States, pp. 1647-1655, Visual Communications and Image Processing '95, Taipei, Taiwan, 95/5/24.
Niimi M, Kamata S, Kawaguchi E. Interactive system for classifying multispectral images using a Hilbert curve. : Proceedings of SPIE - The International Society for Optical Engineering. 3/- 版 巻 2501 . Bellingham, WA, United States: Society of Photo-Optical Instrumentation Engineers. 1995. p. 1647-1655
Niimi, Michiharu ; Kamata, Seiichiro ; Kawaguchi, Eiji. / Interactive system for classifying multispectral images using a Hilbert curve. Proceedings of SPIE - The International Society for Optical Engineering. 巻 2501 3/-. 版 Bellingham, WA, United States : Society of Photo-Optical Instrumentation Engineers, 1995. pp. 1647-1655
@inproceedings{51eefc7e3e3c4e6eb74e4cb014ffcc2e,
title = "Interactive system for classifying multispectral images using a Hilbert curve",
abstract = "There are several techniques for analyzing multispectral images. In general, those are performed by linear transformation methods. In this paper, we present a new interactive method for classifying multispectral images using a Hilbert curve which is a one-to-one mapping from N- dimensional space to one dimensional space and preserves the neighborhood as much as possible. The merit of our system is that the user can extract clusters without computing any distance in N- dimensional space, and analyze multidimensional data from gross data distribution to fine data distribution hierarchically. In the experiments using LANDSAT TM data, it is confirmed that the user can get the real time response from the system after once making the data tables, and understand distribution of data that correspond to categories in feature space.",
author = "Michiharu Niimi and Seiichiro Kamata and Eiji Kawaguchi",
year = "1995",
language = "English",
isbn = "0819418587",
volume = "2501",
pages = "1647--1655",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "Society of Photo-Optical Instrumentation Engineers",
edition = "3/-",

}

TY - GEN

T1 - Interactive system for classifying multispectral images using a Hilbert curve

AU - Niimi, Michiharu

AU - Kamata, Seiichiro

AU - Kawaguchi, Eiji

PY - 1995

Y1 - 1995

N2 - There are several techniques for analyzing multispectral images. In general, those are performed by linear transformation methods. In this paper, we present a new interactive method for classifying multispectral images using a Hilbert curve which is a one-to-one mapping from N- dimensional space to one dimensional space and preserves the neighborhood as much as possible. The merit of our system is that the user can extract clusters without computing any distance in N- dimensional space, and analyze multidimensional data from gross data distribution to fine data distribution hierarchically. In the experiments using LANDSAT TM data, it is confirmed that the user can get the real time response from the system after once making the data tables, and understand distribution of data that correspond to categories in feature space.

AB - There are several techniques for analyzing multispectral images. In general, those are performed by linear transformation methods. In this paper, we present a new interactive method for classifying multispectral images using a Hilbert curve which is a one-to-one mapping from N- dimensional space to one dimensional space and preserves the neighborhood as much as possible. The merit of our system is that the user can extract clusters without computing any distance in N- dimensional space, and analyze multidimensional data from gross data distribution to fine data distribution hierarchically. In the experiments using LANDSAT TM data, it is confirmed that the user can get the real time response from the system after once making the data tables, and understand distribution of data that correspond to categories in feature space.

UR - http://www.scopus.com/inward/record.url?scp=0029238188&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029238188&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029238188

SN - 0819418587

VL - 2501

SP - 1647

EP - 1655

BT - Proceedings of SPIE - The International Society for Optical Engineering

PB - Society of Photo-Optical Instrumentation Engineers

CY - Bellingham, WA, United States

ER -