A simple and effective clustering algorithm for multispectral images using space-filling curves

Jian Zhang, Seiichiro Kamata

Research output: Contribution to journalArticle

Abstract

With the wide usage of multispectral images, a fast efficient multidimensional clustering method becomes not only meaningful but also necessary. In general, to speed up the multidimensional images' analysis, a multidimensional feature vector should be transformed into a lower dimensional space. The Hilbert curve is a continuous one-to-one mapping from N-dimensional space to one-dimensional space, and can preserves neighborhood as much as possible. However, because the Hilbert curve is generated by a recurve division process, 'Boundary Effects' will happen, which means data that are close in N-dimensional space may not be close in one-dimensional Hilbert order. In this paper, a new efficient approach based on the space-filling curves is proposed for classifying multispectral satellite images. In order to remove 'Boundary Effects' of the Hilbert curve, multiple Hilbert curves, z curves, and the Pseudo-Hilbert curve are used jointly. The proposed method extracts category clusters from one-dimensional data without computing any distance in N-dimensional space. Furthermore, multispectral images can be analyzed hierarchically from coarse data distribution to fine data distribution in accordance with different application. The experimental results performed on LANDSAT data have demonstrated that the proposed method is efficient to manage the multispectral images and can be applied easily.

Original languageEnglish
Pages (from-to)1749-1757
Number of pages9
JournalIEICE Transactions on Information and Systems
VolumeE95-D
Issue number7
DOIs
Publication statusPublished - 2012 Jul

Fingerprint

Clustering algorithms
Image analysis
Satellites

Keywords

  • Data clustering
  • Euclidean distance
  • Multispectral images
  • Space-filling curves

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Software
  • Artificial Intelligence
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition

Cite this

A simple and effective clustering algorithm for multispectral images using space-filling curves. / Zhang, Jian; Kamata, Seiichiro.

In: IEICE Transactions on Information and Systems, Vol. E95-D, No. 7, 07.2012, p. 1749-1757.

Research output: Contribution to journalArticle

@article{d6456bdfb67e43d8a36cf1172411334f,
title = "A simple and effective clustering algorithm for multispectral images using space-filling curves",
abstract = "With the wide usage of multispectral images, a fast efficient multidimensional clustering method becomes not only meaningful but also necessary. In general, to speed up the multidimensional images' analysis, a multidimensional feature vector should be transformed into a lower dimensional space. The Hilbert curve is a continuous one-to-one mapping from N-dimensional space to one-dimensional space, and can preserves neighborhood as much as possible. However, because the Hilbert curve is generated by a recurve division process, 'Boundary Effects' will happen, which means data that are close in N-dimensional space may not be close in one-dimensional Hilbert order. In this paper, a new efficient approach based on the space-filling curves is proposed for classifying multispectral satellite images. In order to remove 'Boundary Effects' of the Hilbert curve, multiple Hilbert curves, z curves, and the Pseudo-Hilbert curve are used jointly. The proposed method extracts category clusters from one-dimensional data without computing any distance in N-dimensional space. Furthermore, multispectral images can be analyzed hierarchically from coarse data distribution to fine data distribution in accordance with different application. The experimental results performed on LANDSAT data have demonstrated that the proposed method is efficient to manage the multispectral images and can be applied easily.",
keywords = "Data clustering, Euclidean distance, Multispectral images, Space-filling curves",
author = "Jian Zhang and Seiichiro Kamata",
year = "2012",
month = "7",
doi = "10.1587/transinf.E95.D.1749",
language = "English",
volume = "E95-D",
pages = "1749--1757",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "7",

}

TY - JOUR

T1 - A simple and effective clustering algorithm for multispectral images using space-filling curves

AU - Zhang, Jian

AU - Kamata, Seiichiro

PY - 2012/7

Y1 - 2012/7

N2 - With the wide usage of multispectral images, a fast efficient multidimensional clustering method becomes not only meaningful but also necessary. In general, to speed up the multidimensional images' analysis, a multidimensional feature vector should be transformed into a lower dimensional space. The Hilbert curve is a continuous one-to-one mapping from N-dimensional space to one-dimensional space, and can preserves neighborhood as much as possible. However, because the Hilbert curve is generated by a recurve division process, 'Boundary Effects' will happen, which means data that are close in N-dimensional space may not be close in one-dimensional Hilbert order. In this paper, a new efficient approach based on the space-filling curves is proposed for classifying multispectral satellite images. In order to remove 'Boundary Effects' of the Hilbert curve, multiple Hilbert curves, z curves, and the Pseudo-Hilbert curve are used jointly. The proposed method extracts category clusters from one-dimensional data without computing any distance in N-dimensional space. Furthermore, multispectral images can be analyzed hierarchically from coarse data distribution to fine data distribution in accordance with different application. The experimental results performed on LANDSAT data have demonstrated that the proposed method is efficient to manage the multispectral images and can be applied easily.

AB - With the wide usage of multispectral images, a fast efficient multidimensional clustering method becomes not only meaningful but also necessary. In general, to speed up the multidimensional images' analysis, a multidimensional feature vector should be transformed into a lower dimensional space. The Hilbert curve is a continuous one-to-one mapping from N-dimensional space to one-dimensional space, and can preserves neighborhood as much as possible. However, because the Hilbert curve is generated by a recurve division process, 'Boundary Effects' will happen, which means data that are close in N-dimensional space may not be close in one-dimensional Hilbert order. In this paper, a new efficient approach based on the space-filling curves is proposed for classifying multispectral satellite images. In order to remove 'Boundary Effects' of the Hilbert curve, multiple Hilbert curves, z curves, and the Pseudo-Hilbert curve are used jointly. The proposed method extracts category clusters from one-dimensional data without computing any distance in N-dimensional space. Furthermore, multispectral images can be analyzed hierarchically from coarse data distribution to fine data distribution in accordance with different application. The experimental results performed on LANDSAT data have demonstrated that the proposed method is efficient to manage the multispectral images and can be applied easily.

KW - Data clustering

KW - Euclidean distance

KW - Multispectral images

KW - Space-filling curves

UR - http://www.scopus.com/inward/record.url?scp=84863422479&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863422479&partnerID=8YFLogxK

U2 - 10.1587/transinf.E95.D.1749

DO - 10.1587/transinf.E95.D.1749

M3 - Article

AN - SCOPUS:84863422479

VL - E95-D

SP - 1749

EP - 1757

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 7

ER -