Salient Pixels and Dimensionality Reduction for Display of Multi/Hyperspectral Images

  • Steven Le Moan
  • Ferdinand Deger
  • Alamin Mansouri
  • Yvon Voisin
  • Jon Y. Hardeberg
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7340)


Dimensionality Reduction (DR) of spectral images is a common approach to different purposes such as visualization, noise removal or compression. Most methods such as PCA or band selection use either the entire population of pixels or a uniformly sampled subset in order to compute a projection matrix. By doing so, spatial information is not accurately handled and all the objects contained in the scene are given the same emphasis. Nonetheless, it is possible to focus the DR on the separation of specific Objects of Interest (OoI), simply by neglecting all the others. In PCA for instance, instead of using the variance of the scene in each spectral channel, we show that it is more efficient to consider the variance of a small group of pixels representing several OoI, which must be separated by the projection. We propose an efficient method based on saliency to automatically identify OoI and extract only a few relevant pixels to enhance the separation foreground/background in the DR process.


Hyperspectral Image Natural Scene Multispectral Image Salient Object Spectral Channel 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Chang, C., Du, Q., Sun, T., Althouse, M.: A joint band prioritization and band-decorrelation approach to band selection for hyperspectral image classification. IEEE Trans. on Geoscience and Remote Sensing 37, 2631–2641 (1999)CrossRefGoogle Scholar
  2. 2.
    Guo, B., Damper, R., Gunn, S., Nelson, J.: A fast separability-based feature-selection method for high-dimensional remotely sensed image classification. Pattern Recognition 41, 1670–1679 (2008)Google Scholar
  3. 3.
    Du, Q., Yang, H.: Similarity-based unsupervised band selection for hyperspectral image analysis. Geoscience and Remote Sensing Letters 5, 564–568 (2008)CrossRefGoogle Scholar
  4. 4.
    Jia, X., Richards, J.: Segmented principal components transformation for efficient hyperspectral remote-sensing image display and classification. IEEE Trans. on Geoscience and Remote Sensing 37, 538–542 (1999)CrossRefGoogle Scholar
  5. 5.
    Tyo, J., Konsolakis, A., Diersen, D., Olsen, R.: Principal-components-based display strategy for spectral imagery. IEEE Trans. on Geoscience and Remote Sensing 41, 708–718 (2003)CrossRefGoogle Scholar
  6. 6.
    Wang, J., Chang, C.: Independent component analysis-based dimensionality reduction with applications in hyperspectral image analysis. IEEE Trans. on Geoscience and Remote Sensing 44, 1586–1600 (2006)CrossRefGoogle Scholar
  7. 7.
    Poldera, G., van der Heijden, G.: Visualization of spectral images. In: Proceedings of SPIE, vol. 4553, p. 133 (2001)Google Scholar
  8. 8.
    Jacobson, N., Gupta, M.: Design goals and solutions for display of hyperspectral images. IEEE Trans. on Geoscience and Remote Sensing 43, 2684–2692 (2005)CrossRefGoogle Scholar
  9. 9.
    Scheunders, P.: Multispectral image fusion using local mapping techniques. In: International Conference on Pattern Recognition, vol. 15, pp. 311–314 (2000)Google Scholar
  10. 10.
    Le Moan, S., Mansouri, A., Hardeberg, J., Voisin, Y.: Saliency in Spectral Images. In: Heyden, A., Kahl, F. (eds.) SCIA 2011. LNCS, vol. 6688, pp. 114–123. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  11. 11.
    Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence 20, 1254–1259 (1998)CrossRefGoogle Scholar
  12. 12.
    Smith, L.: A tutorial on principal components analysis, vol. 51, p. 52. Cornell University, USA (2002)Google Scholar
  13. 13.
    Nascimento, S., Ferreira, F., Foster, D.: Statistics of spatial cone-excitation ratios in natural scenes. Journal of the Optical Society of America A 19, 1484–1490 (2002)CrossRefGoogle Scholar
  14. 14.
    Cai, S., Du, Q., Moorhead, R.: Hyperspectral imagery visualization using double layers. IEEE Trans. on Geoscience and Remote Sensing 45, 3028–3036 (2007)CrossRefGoogle Scholar
  15. 15.
    Le Moan, S., Mansouri, A., Voisin, Y., Hardeberg, J.Y.: A constrained band selection method based on information measures for spectral image color visualization. Transactions on Geoscience and Remote Sensing 49, 5104–5115 (2011)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Steven Le Moan
    • 1
    • 2
  • Ferdinand Deger
    • 1
    • 2
  • Alamin Mansouri
    • 1
  • Yvon Voisin
    • 1
  • Jon Y. Hardeberg
    • 2
  1. 1.Laboratoire d’Electronique, Informatique et ImageUniversité de BourgogneAuxerreFrance
  2. 2.The Norwegian Color Research LaboratoryGjøvik University CollegeNorway

Personalised recommendations