Unsupervised segmentation of hyperspectral images based on dominant edges

Sangwook Lee, Sanghun Lee, Chul Hee Lee

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

1 Citation (Scopus)

Abstract

In this paper, we propose a new unsupervised segmentation method for hyperspectral images based on dominant edge information. In the proposed algorithm, we first apply the principal component analysis and select the dominant eigenimages. Then edge operators and the histogram equalizer are applied to the selected eigenimages, which produces edge images. By combining these edge images, we obtain a binary edge image. Morphological operations are then applied to these binary edge image to remove erroneous edges. Experimental results show that the proposed algorithm produced satisfactory results without any user input.

Original languageEnglish
Title of host publicationVISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications
PublisherSciTePress
Pages588-592
Number of pages5
ISBN (Print)9789897580031
Publication statusPublished - 2014 Jan 1
Event9th International Conference on Computer Vision Theory and Applications, VISAPP 2014 - Lisbon, Portugal
Duration: 2014 Jan 52014 Jan 8

Publication series

NameVISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications
Volume1

Other

Other9th International Conference on Computer Vision Theory and Applications, VISAPP 2014
CountryPortugal
CityLisbon
Period14/1/514/1/8

Fingerprint

Equalizers
Principal component analysis

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Lee, S., Lee, S., & Lee, C. H. (2014). Unsupervised segmentation of hyperspectral images based on dominant edges. In VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications (pp. 588-592). (VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications; Vol. 1). SciTePress.
Lee, Sangwook ; Lee, Sanghun ; Lee, Chul Hee. / Unsupervised segmentation of hyperspectral images based on dominant edges. VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications. SciTePress, 2014. pp. 588-592 (VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications).
@inproceedings{d38fbe7f7395450f897ef597ebf46fc0,
title = "Unsupervised segmentation of hyperspectral images based on dominant edges",
abstract = "In this paper, we propose a new unsupervised segmentation method for hyperspectral images based on dominant edge information. In the proposed algorithm, we first apply the principal component analysis and select the dominant eigenimages. Then edge operators and the histogram equalizer are applied to the selected eigenimages, which produces edge images. By combining these edge images, we obtain a binary edge image. Morphological operations are then applied to these binary edge image to remove erroneous edges. Experimental results show that the proposed algorithm produced satisfactory results without any user input.",
author = "Sangwook Lee and Sanghun Lee and Lee, {Chul Hee}",
year = "2014",
month = "1",
day = "1",
language = "English",
isbn = "9789897580031",
series = "VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications",
publisher = "SciTePress",
pages = "588--592",
booktitle = "VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications",

}

Lee, S, Lee, S & Lee, CH 2014, Unsupervised segmentation of hyperspectral images based on dominant edges. in VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications. VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications, vol. 1, SciTePress, pp. 588-592, 9th International Conference on Computer Vision Theory and Applications, VISAPP 2014, Lisbon, Portugal, 14/1/5.

Unsupervised segmentation of hyperspectral images based on dominant edges. / Lee, Sangwook; Lee, Sanghun; Lee, Chul Hee.

VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications. SciTePress, 2014. p. 588-592 (VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications; Vol. 1).

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

TY - GEN

T1 - Unsupervised segmentation of hyperspectral images based on dominant edges

AU - Lee, Sangwook

AU - Lee, Sanghun

AU - Lee, Chul Hee

PY - 2014/1/1

Y1 - 2014/1/1

N2 - In this paper, we propose a new unsupervised segmentation method for hyperspectral images based on dominant edge information. In the proposed algorithm, we first apply the principal component analysis and select the dominant eigenimages. Then edge operators and the histogram equalizer are applied to the selected eigenimages, which produces edge images. By combining these edge images, we obtain a binary edge image. Morphological operations are then applied to these binary edge image to remove erroneous edges. Experimental results show that the proposed algorithm produced satisfactory results without any user input.

AB - In this paper, we propose a new unsupervised segmentation method for hyperspectral images based on dominant edge information. In the proposed algorithm, we first apply the principal component analysis and select the dominant eigenimages. Then edge operators and the histogram equalizer are applied to the selected eigenimages, which produces edge images. By combining these edge images, we obtain a binary edge image. Morphological operations are then applied to these binary edge image to remove erroneous edges. Experimental results show that the proposed algorithm produced satisfactory results without any user input.

UR - http://www.scopus.com/inward/record.url?scp=84906914280&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906914280&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84906914280

SN - 9789897580031

T3 - VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications

SP - 588

EP - 592

BT - VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications

PB - SciTePress

ER -

Lee S, Lee S, Lee CH. Unsupervised segmentation of hyperspectral images based on dominant edges. In VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications. SciTePress. 2014. p. 588-592. (VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications).