A Hierarchical Texture Model for Unsupervised Segmentation of Remotely Sensed Images

  • Giuseppe Scarpa
  • Michal Haindl
  • Josiane Zerubia
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4522)

Abstract

In this work a novel texture model particularly suited for unsupervised image segmentation is proposed. Any texture is represented at region level by means of a finite-state hierarchical model resulting from the superposition of several Markov chains, each associated with a different spatial direction. Corresponding to such a modeling, an optimization scheme, referred to as Texture Fragmentation and Reconstruction (TFR) algorithm, has been introduced.

The TFR addresses the model estimation problem in two sequential layers: the former “fragmentation” step allows to find the terminal states of the model, while the latter “reconstruction” step is aimed at estimating the relationships among the states which provide the optimal hierarchical structure to associate with the model. The latter step is based on a probabilistic measure, i.e, the region gain, which accounts for both the region scale and the inter-region interaction.

The proposed segmentation algorithm was tested on a segmentation benchmark and applied to high resolution remote-sensing forest images as well.

Keywords

Segmentation texture model Markov chain remote sensing forest classification 

References

  1. 1.
    Carson, C., Thomas, M., Belongie, S., Hellerstein, J.M., Malik, J.: Blobworld: A System for Region-Based Image Indexing and Retrieval. In: Huijsmans, D.P., Smeulders, A.W.M. (eds.) VISUAL 1999. LNCS, vol. 1614, pp. 509–517. Springer, Heidelberg (1999)Google Scholar
  2. 2.
    D’Elia, C., Poggi, G., Scarpa, G.: A Tree-Structured Markov random field model for Bayesian image segmentation. IEEE Transactions on Image Processing 12(10), 1259–1273 (2003)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Haindl, M., Mikeš, S.: Colour texture segmentation using modelling approach. In: Singh, S., Singh, M., Apte, C., Perner, P. (eds.) ICAPR 2005. LNCS, vol. 3687, pp. 484–491. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  4. 4.
    Poggi, G., Scarpa, G., Zerubia, J.: Supervised segmentation of remote-sensing images based on a tree-structured MRF model. IEEE Transactions on Geoscience and Remote Sensing 43(8), 1901–1911 (2005)CrossRefGoogle Scholar
  5. 5.
    Beaulieu, J.-M., Touzi, R.: Segmentation of textured polarimetric SAR scenes by likelihood approximation. IEEE Transactions on Geoscience and Remote Sensing 42(10), 2063–2072 (2004)CrossRefGoogle Scholar
  6. 6.
    Hese, S.: Segmentation of forest stands in very high resolution stereo data. In: Proc. IGARSS’01, vol. 4, Sydney, Australia, July 2001, pp. 1654–1656 (2001)Google Scholar
  7. 7.
    Mikeš, S., Haindl, M.: Prague texture segmentation data generator and benchmark. ERCIM News 64, 67–68 (2006), http://mosaic.utia.cas.cz Google Scholar
  8. 8.
    Haindl, M., Mikeš, S.: Model-based texture segmentation. In: Campilho, A.C., Kamel, M. (eds.) ICIAR 2004. LNCS, vol. 3212, pp. 306–313. Springer, Heidelberg (2004)Google Scholar
  9. 9.
    Deng, Y., Manjunath, B.S.: Unsupervised Segmentation of Color-Texture Regions in Images and Video. IEEE Transactions on Pattern Analysis Machine Intelligence 23(8), 800–810 (2001)CrossRefGoogle Scholar
  10. 10.
    Christoudias, C.M., Georgescu, B., Meer, P.: Synergism in Low Level Vision. In: Proc. 16th ICPR, vol. 4, Los Alamitos, August 2002, pp. 150–155 (2002)Google Scholar
  11. 11.
    Fischer, B., Thies, C.J., Guld, M.O., Lehmann, T.M.: Content-based image retrieval by matching hierarchical attributed region adjacency graphs. Proc. SPIE 5370, 598–606 (2004)CrossRefGoogle Scholar
  12. 12.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. Wiley, Chichester (2000)Google Scholar
  13. 13.
    Scarpa, G., Haindl, M.: Unsupervised Texture Segmentation by Spectral-Spatial-Independent Clustering. In: Proc. 18th ICPR, vol. 2, Hong Kong, China, August 2006, pp. 151–154 (2006)Google Scholar
  14. 14.
    Penny, W.D.: Kullback-Leibler divergences of normal, Gamma, Dirichlet and Wishart densities. Technical report, Wellcome Department of Imaging Neuroscience, University College London (UK) (2001)Google Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Giuseppe Scarpa
    • 1
    • 2
  • Michal Haindl
    • 2
  • Josiane Zerubia
    • 1
  1. 1.ARIANA Research Group, INRIA/I3S, Sophia AntipolisFrance
  2. 2.Pattern Recognition Dep., ÚTIA, Academy of Sciences, PragueCzech Republic

Personalised recommendations