High-Dimensional Spectral Feature Selection for 3D Object Recognition Based on Reeb Graphs

  • Boyan Bonev
  • Francisco Escolano
  • Daniela Giorgi
  • Silvia Biasotti
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6218)


In this work we evaluate purely structural graph measures for 3D object classification. We extract spectral features from different Reeb graph representations and successfully deal with a multi-class problem. We use an information-theoretic filter for feature selection. We show experimentally that a small change in the order of selection has a significant impact on the classification performance and we study the impact of the precision of the selection criterion. A detailed analysis of the feature participation during the selection process helps us to draw conclusions about which spectral features are most important for the classification problem.


Feature Selection Mutual Information Triangle Mesh Entropy Estimation Commute Time 
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.
    Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. Journal of Machine Learning Research 3, 1157–1182 (2003)zbMATHCrossRefGoogle Scholar
  2. 2.
    Luo, B., Wilson, R., Hancock, E.: Spectral embedding of graphs. Pattern Recognition 36(10), 2213–2223 (2003)zbMATHCrossRefGoogle Scholar
  3. 3.
    Biasotti, S.: Topological coding of surfaces with boundary using Reeb graphs. Computer Graphics and Geometry 7(1), 31–45 (2005)Google Scholar
  4. 4.
    Escolano, F., Suau, P., Bonev, B.: Information Theory in Computer Vision and Pattern Recognition. Springer, New York (2009)zbMATHCrossRefGoogle Scholar
  5. 5.
    Reeb, G.: Sur les points singuliers d’une forme de Pfaff complètement intégrable ou d’une fonction numérique. Comptes Rendus 222, 847–849 (1946)zbMATHMathSciNetGoogle Scholar
  6. 6.
    Biasotti, S., Giorgi, D., Spagnuolo, M., Falcidieno, B.: Reeb graphs for shape analysis and applications. Theoretical Computer Science 392(1–3), 5–22 (2008), doi:10.1016/j.tcs.2007.10.018.zbMATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Biasotti, S.: Computational Topology Methods for Shape Modelling Applications. PhD thesis, Universitá degli Studi di Genova (May 2004)Google Scholar
  8. 8.
    Hilaga, M., Shinagawa, Y., Kohmura, T., Kunii, T.L.: Topology matching for fully automatic similarity estimation of 3D shapes. In: SIGGRAPH 2001, Los Angeles, CA, pp. 203–212 (2001)Google Scholar
  9. 9.
    Attene, M., Biasotti, S.: Shape retrieval contest 2008: Stability of watertight models. In: SMI 2008, pp. 219–220 (2008)Google Scholar
  10. 10.
    Barabási, A.L., Bonabeau, E.: Scale-free networks. Scientific American 288, 50–59 (2003)CrossRefGoogle Scholar
  11. 11.
    Estrada, E., Rodriguez, J.A.: Subgraph centrality in complex networks. Physical Review E 71(5) (2005)Google Scholar
  12. 12.
    Qiu, H., Hancock, E.R.: Clustering and embedding using commute times. IEEE Transactions on PAMI 29(11), 1873–1890 (2007)Google Scholar
  13. 13.
    Escolano, F., Giorgi, D., Hancock, E.R., Lozano, M.A., Falcidieno, B.: Flow complexity: Fast polytopal graph complexity and 3d object clustering. In: GbRPR, pp. 253–262 (2009)Google Scholar
  14. 14.
    Escolano, F., Hancock, E.R., Lozano, M.A.: Birkhoff polytopes, heat kernels and graph complexity. In: ICPR, pp. 1–5 (2008)Google Scholar
  15. 15.
    Leonenko, N., Pronzato, L., Savani, V.: A class of rényi information estimators for multidimensional densities. The Annals of Statistics 36(5), 2153–2182 (2008)zbMATHCrossRefMathSciNetGoogle Scholar
  16. 16.
    Bonev, B., Escolano, F., Cazorla, M.: Feature selection, mutual information, and the classification of high-dimensional patterns. Pattern Analysis and Applications (February 2008)Google Scholar
  17. 17.
    Mount, D., Arya, S.: Ann: A library for approximate nearest neighbor searching (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Boyan Bonev
    • 1
  • Francisco Escolano
    • 1
  • Daniela Giorgi
    • 2
  • Silvia Biasotti
    • 2
  1. 1.University of AlicanteSpain
  2. 2.IMATI CNRGenovaItaly

Personalised recommendations