Unsupervised Segmentation of Hyperspectral Images based on Dominant Edges

Sangwook Lee, Sanghun Lee, Chulhee Lee

2014

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.

References

  1. Acito N, Corsini G and Diani M 2000. An unsupervised algorithm for hyperspectral image segmentation based on the Gaussian mixture model. in Proc, IGARSS, pp. 3745-3747.
  2. Cao F, Hong W, Wu Y and Pottier E 2007. An Unsupervised Segmentation With an Adaptive Number of Clusters Using the SPAN/H/a/A Space and the Complex Wishart Clustering for Fully Polarimetric SAR Data Analysis. IEEE Trans., Geosci. Remote Sens., vol. 45, no.11, pp. 3454-3467.
  3. Erturk A and Erturk S 2006 . Unsupervised Segmentation of Hyperspectral Images Using Modified Phase Correlation. IEEE Geosci. Remote Sens. Lett., vol. 3, no. 4, pp. 527-531.
  4. Guo B. Gunn S. R. and Damper R. I. 2006. Band Selection for Hyperspectral Image Classification Using Mutual Information. IEEE Geosci. Remote Sens. Lett., vol. 3, no. 4, pp. 522-526.
  5. Ifrarraguerri A and Chang C. I. 1999. Multispectral and hyperspectral image analysis with convex cones. IEEE Trans., Geosci. Remote Sens., vol. 37, no. 2, pp. 756 - 770.
  6. Lim S, Sohn K and Lee C 2001. Principal Component Analysis for Compression of Hyperspectral Images. Proc. IEEE IGARSS, vol. 1, pp. 97-99.
  7. Masson P and Pieczynski W 1993. SEM algorithm and unsupervised statistical segmentation of satellite images. IEEE Trans., Geosci, and Remote Sens., vol. 31, no. 3, pp. 618- 633.
  8. Meyer A, Paglieroni D and Astaneh C 2003. K-means reclustering: Algorithmic options with quantifiable performance comparisons. Proceedings of the SPIE, Volume 5001, pp. 84-92.
  9. Pesaresi M and Benediktsson A 2001. A New Approach for the Morphological Segmentation of HighResolution Satellite Imagery. IEEE Trans., Geosci. Remote Sens., vol. 39, no. 2, pp. 309-320.
  10. Robert AS 1997. Remote sensing: models and methods for image processing. Academic Press, 2nd edit., pp. 389- 447.
  11. Sarkar A, Biswas M. K. and Kartikeyan B 2002. A MRF Model-Based segmentation Approach to classification for Multispectral imagery. IEEE Trans., Geosci. Remote Sens., vol. 40, no. 5, pp. 1102-1113.
  12. Tarabalka Y, Chanussot J, and Benediktsson J. A. 2010. Segmentation and Classification of Hyperspectral Images Using Minimum Spanning Forest Grown From Automatically Selected Markers. IEEE Trans. Systems, Man, and Cybernetics-PART B: Cybernetics, vol. 40, no. 5, pp. 1267 - 1279.
  13. Tarabalka Y, Chanussota J, and Benediktsson JA 2010. Segmentation and classification of hyperspectral images using watershed transformation. Pattern Recognition, vol. 43, Iss. 7, pp. 2367-2379.
  14. Wang S, Yan F, Zhu L, Wang L and Jiao Y 2003. Water quality monitoring using hyperspectral remote sensing data in Taihu Lake China. Proc., IGARSS, pp. 4553- 4556.
Download


Paper Citation


in Harvard Style

Lee S., Lee S. and Lee C. (2014). Unsupervised Segmentation of Hyperspectral Images based on Dominant Edges . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-003-1, pages 588-592. DOI: 10.5220/0004739705880592


in Bibtex Style

@conference{visapp14,
author={Sangwook Lee and Sanghun Lee and Chulhee Lee},
title={Unsupervised Segmentation of Hyperspectral Images based on Dominant Edges},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={588-592},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004739705880592},
isbn={978-989-758-003-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014)
TI - Unsupervised Segmentation of Hyperspectral Images based on Dominant Edges
SN - 978-989-758-003-1
AU - Lee S.
AU - Lee S.
AU - Lee C.
PY - 2014
SP - 588
EP - 592
DO - 10.5220/0004739705880592