Unsupervised segmentation of hyperspectral images

Sangwook Lee, Chul Hee Lee

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

3 Citations (Scopus)

Abstract

In this paper, we propose a new unsupervised segmentation method for hyperspectral images using edge fusion. We first remove noisy spectral band images by examining the correlations between the spectral bands. Then, the Canny algorithm is applied to the retained images. This procedure produces a number of edge images. To combine these edge images, we compute an average edge image and then apply a thresholding operation to obtain a binary edge image. By applying dilation and region filling procedures to the binary edge image, we finally obtain a segmented image. Experimental results show that the proposed algorithm produced satisfactory segmentation results without requiring user input.

Original languageEnglish
Title of host publicationSatellite Data Compression, Communication, and Processing IV
DOIs
Publication statusPublished - 2008 Nov 21
EventSatellite Data Compression, Communication, and Processing IV - San Diego, CA, United States
Duration: 2008 Aug 102008 Aug 11

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume7084
ISSN (Print)0277-786X

Other

OtherSatellite Data Compression, Communication, and Processing IV
CountryUnited States
CitySan Diego, CA
Period08/8/1008/8/11

Fingerprint

Hyperspectral Image
Segmentation
Fusion reactions
spectral bands
Binary
Thresholding
Dilation
Fusion
fusion
Experimental Results

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Lee, S., & Lee, C. H. (2008). Unsupervised segmentation of hyperspectral images. In Satellite Data Compression, Communication, and Processing IV [70840B] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 7084). https://doi.org/10.1117/12.795807
Lee, Sangwook ; Lee, Chul Hee. / Unsupervised segmentation of hyperspectral images. Satellite Data Compression, Communication, and Processing IV. 2008. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{f8c8a6307e644b3c9cbe7d8c38411176,
title = "Unsupervised segmentation of hyperspectral images",
abstract = "In this paper, we propose a new unsupervised segmentation method for hyperspectral images using edge fusion. We first remove noisy spectral band images by examining the correlations between the spectral bands. Then, the Canny algorithm is applied to the retained images. This procedure produces a number of edge images. To combine these edge images, we compute an average edge image and then apply a thresholding operation to obtain a binary edge image. By applying dilation and region filling procedures to the binary edge image, we finally obtain a segmented image. Experimental results show that the proposed algorithm produced satisfactory segmentation results without requiring user input.",
author = "Sangwook Lee and Lee, {Chul Hee}",
year = "2008",
month = "11",
day = "21",
doi = "10.1117/12.795807",
language = "English",
isbn = "9780819473042",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
booktitle = "Satellite Data Compression, Communication, and Processing IV",

}

Lee, S & Lee, CH 2008, Unsupervised segmentation of hyperspectral images. in Satellite Data Compression, Communication, and Processing IV., 70840B, Proceedings of SPIE - The International Society for Optical Engineering, vol. 7084, Satellite Data Compression, Communication, and Processing IV, San Diego, CA, United States, 08/8/10. https://doi.org/10.1117/12.795807

Unsupervised segmentation of hyperspectral images. / Lee, Sangwook; Lee, Chul Hee.

Satellite Data Compression, Communication, and Processing IV. 2008. 70840B (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 7084).

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

TY - GEN

T1 - Unsupervised segmentation of hyperspectral images

AU - Lee, Sangwook

AU - Lee, Chul Hee

PY - 2008/11/21

Y1 - 2008/11/21

N2 - In this paper, we propose a new unsupervised segmentation method for hyperspectral images using edge fusion. We first remove noisy spectral band images by examining the correlations between the spectral bands. Then, the Canny algorithm is applied to the retained images. This procedure produces a number of edge images. To combine these edge images, we compute an average edge image and then apply a thresholding operation to obtain a binary edge image. By applying dilation and region filling procedures to the binary edge image, we finally obtain a segmented image. Experimental results show that the proposed algorithm produced satisfactory segmentation results without requiring user input.

AB - In this paper, we propose a new unsupervised segmentation method for hyperspectral images using edge fusion. We first remove noisy spectral band images by examining the correlations between the spectral bands. Then, the Canny algorithm is applied to the retained images. This procedure produces a number of edge images. To combine these edge images, we compute an average edge image and then apply a thresholding operation to obtain a binary edge image. By applying dilation and region filling procedures to the binary edge image, we finally obtain a segmented image. Experimental results show that the proposed algorithm produced satisfactory segmentation results without requiring user input.

UR - http://www.scopus.com/inward/record.url?scp=56249138330&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56249138330&partnerID=8YFLogxK

U2 - 10.1117/12.795807

DO - 10.1117/12.795807

M3 - Conference contribution

AN - SCOPUS:56249138330

SN - 9780819473042

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Satellite Data Compression, Communication, and Processing IV

ER -

Lee S, Lee CH. Unsupervised segmentation of hyperspectral images. In Satellite Data Compression, Communication, and Processing IV. 2008. 70840B. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.795807