Segmentation of Hyperspectral Images by Tuned Chromatic Watershed

Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 234)


This work presents a segmentation method for multidimensional images, therefore it is valid for standard Red, Green, Blue (RGB) images, multi-spectral images or hyperspectral images. On the one hand it is based in a tuned version of watershed transform, and on the other hand it is based on a chromatic gradient that is made through Hyperspherical Coordinates. A remarkable feature of this algorithm is its robustness; it outperforms the natural oversegmentation induced by the standard watershed. Another important property of this algorithm is its robustness respect changes on the intensity: shines and shadows. Inspired on the Human Vision System (HVS) this algorithm provides segmentations according with the user expectations, where homogeneous chromatic regions of an image corespond with homogeneous convex regions of the output.


Hyperspherical Coordinates   Hyperspectral Chromatic Gradient    Watershed Transformation Hyperspectral Image Segmentation Computer Vision Edge Detection 



This work has been done thanks to the grant BFI08.271 of the Basque Country Government. This work was partially supported by the computing facilities of Dichromatic Reflection Model (CETA-CIEMAT), funded by the European Regional Development Fund (ERDF).


  1. 1.
    Moreno, R., A. D’Anjou.: Hyperspectral image segmentation by t-watershed and hyperspherical coordinates. In: Graa, M., Toro, C., Posada, J., Howlett, R.J., Jain, L.C. (eds.) KES. Frontiers in Artificial Intelligence and Applications, vol. 243, pp. 2114–2121, IOS Press, Amsterdam (2012)Google Scholar
  2. 2.
    Moreno, R., Graa, M., Zulueta.: RGB colour gradient following colour constancy preservation. Electron. Lett. 46(13), 908–910 (2010)Google Scholar
  3. 3.
    Borges, J.S., Bioucas-Dias, J.M., Marcal, A.R.: Bayesian hyperspectral image segmentation with discriminative class learning. IEEE Trans. Geosci. Remote Sens. 49, 2151–2164 (2011)CrossRefGoogle Scholar
  4. 4.
    Li J., Bioucas-Dias, J.M., Plaza, A.: Spectral-spatial hyperspectral image segmentation using subspace multinomial logistic regression and markov random fields. IEEE Trans. Geosci. Remote Sens. 50(3), 809–823 (2012)Google Scholar
  5. 5.
    Bilgin, G., Erturk, S., Yildirim, T.: Segmentation of hyperspectral images via subtractive clustering and cluster validation using One-Class support vector machines. IEEE Trans. Geosci. Remote Sens. 49, 2936–2944 (2011)CrossRefGoogle Scholar
  6. 6.
    Ball, J.E., West, T., Prasad, S., Bruce, L.M.: Level set hyperspectral image segmentation using spectral information divergence-based best band selection. In: Geoscience and Remote Sensing Symposium, 2007. IGARSS 2007. IEEE International, IEEE, 4053–4056 July 2007Google Scholar
  7. 7.
    Gorretta, N., Roger, J.M., Rabatel, G., Bellon-Maurel, V., Fiorio, C., Lelong, C.: Hyperspectral image segmentation: the butterfly approach. In: First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, 2009. WHISPERS ’09, IEEE, pp. 1–4, Aug 2009Google Scholar
  8. 8.
    Li, J., Bioucas-Dias, J.M., Plaza, A.: Semi-supervised hyperspectral image segmentation. In: First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, 2009. WHISPERS ’09, IEEE, pp. 1–4, Aug 2009Google Scholar
  9. 9.
    Li, J., Bioucas-Dias, J.M., Plaza, A.: Semisupervised hyperspectral image segmentation using multinomial logistic regression with active learning. IEEE Trans. Geosci. Remote Sens. 48, 4085–4098 (2010)Google Scholar
  10. 10.
    Tarabalka, Y., Chanussot, J., Benediktsson, J.A.: Segmentation and classification of hyperspectral images using watershed transformation. Pattern Recogn. 43(7), 2367–2379 (2010)CrossRefMATHGoogle Scholar
  11. 11.
    Dinh, V., Leitner, R., Paclik, P., and Duin, R.: A clustering based method for edge detection in hyperspectral images. In: Salberg, A.-B., Hardeberg, J., Jenssen R. (eds.) Image Analysis, Lecture Notes in Computer Science. vol. 5575, pp. 580–587. Springer, Heidelberg (2009)Google Scholar
  12. 12.
    Lee, M.A., Bruce, L.M.: Applying cellular automata to hyperspectral edge detection. .In: Geoscience and Remote Sensing Symposium (IGARSS), 2010 IEEE International, IEEE, pp. 2202–2205, July 2010Google Scholar
  13. 13.
    Luo, W., Zhong, L.: Spectral similarity measure edge detection algorithm in hyperspectral image. In: 2nd International Congress on Image and Signal Processing, 2009. CISP ’09, IEEE, pp. 1–4, Oct 2009Google Scholar
  14. 14.
    Beucher, S., Lantuejoul, C.: Use of watersheds in contour detection. In: International Workshop on Image Processing: Real-time Edge and Motion Detection/Estimation, Rennes. France, Sept 1979Google Scholar
  15. 15.
    Elwaseif, M., Slater, L.: Quantifying tomb geometries in resistivity images using watershed algorithms. J. Archaeol. Sci. 37(7), 1424–1436 (2010)CrossRefGoogle Scholar
  16. 16.
    Dagher, I., Tom, K.E.: Waterballoons: A hybrid watershed balloon snake segmentation. Image Vis. Comput. 26(7), 905–912 (2008)CrossRefGoogle Scholar
  17. 17.
    Shafer, S.A.: Using color to separate reflection components. Color Res. appl. 10, 43–51 1984Google Scholar
  18. 18.
    Hapke, B.: Bidirectional reflectance spectroscopy.1. theory. J. Geophys. Res. 86, 3039–3054 (1981)CrossRefGoogle Scholar
  19. 19.
    Yang, L., Zhao, D., Wu, X., Li, H., Zhai, J.: An improved prewitt algorithm for edge detection based on noised image. In: Image and Signal Processing (CISP), 2011 4th International Congress on, vol. 3, pp. 1197–1200, Oct 2011Google Scholar
  20. 20.
    Lavoie, T., Merlo, E.: An accurate estimation of the levenshtein distance using metric trees and manhattan distance. In: Software Clones (IWSC), 2012 6th International Workshop on, pp. 1–7, June 2012Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.Computational Intelligence GroupUniversidad del País VascoDonostia-San SebastiánSpain

Personalised recommendations