Signal, Image and Video Processing

, Volume 7, Issue 3, pp 467–478 | Cite as

Information measures for object understanding

Original Paper

Abstract

In this paper, we present a new information-theoretic framework for object understanding. From a visibility channel between a set of viewpoints and the polygons of an object, and three specific information measures introduced in the field of neural systems, we analyze and visualize the information associated with an object. Our approach is twofold since we present several forms of representing the shape information in the object space and different ways of capturing this information from the viewpoint space. First, we introduce several information measures associated with the polygons of the object. The way we visualize, this polygonal information provides us with different forms of perceiving the shape of the object. Second, we present several ways of evaluating the shape information from the observer’s point of view. To do this, the polygonal information is “projected” onto the viewpoints to quantify the information associated with a viewpoint and is used to select the \(N\) best views and to explore the object. A number of experiments show the behavior of all proposed measures.

Keywords

Information theory Ambient occlusion Obscurances  Viewpoint selection Object exploration 

References

  1. 1.
    Blanz, V., Tarr, M., Bülthoff, H.: What object attributes determine canonical views? Perception 28, 575–599 (1999)CrossRefGoogle Scholar
  2. 2.
    Bonaventura, X., Feixas, M., Sbert, M.: Viewpoint information. In: 21st GraphiCon International Conference on Computer Graphics and Vision, pp. 16–19 (2011)Google Scholar
  3. 3.
    Bordoloi, U.D., Shen, H.W.: Viewpoint evaluation for volume rendering. In: IEEE Visualization 2005, pp. 487–494 (2005)Google Scholar
  4. 4.
    Butts, D.A.: How much information is associated with a particular stimulus? Netw. Comput. Neural Syst. 14, 177–187 (2003)CrossRefGoogle Scholar
  5. 5.
    Cover, T.M., Thomas, J.A.: Elements of Information Theory. Wiley Series in Telecommunications, New York (1991)MATHCrossRefGoogle Scholar
  6. 6.
    Deweese, M.R., Meister, M.: How to measure the information gained from one symbol. Netw. Comput. Neural Syst. 10(4), 325–340 (1999)MATHCrossRefGoogle Scholar
  7. 7.
    Feixas, M., Sbert, M., González, F.: A unified information-theoretic framework for viewpoint selection and mesh saliency. ACM Trans. Appl. Percept. 6(1), 1–23 (2009) Google Scholar
  8. 8.
    Furuichi, S.: Information theoretical properties of tsallis entropies. J. Math. Phys. 47(2), 1–18 (2006)MathSciNetCrossRefGoogle Scholar
  9. 9.
    González, F., Sbert, M., Feixas, M.: Viewpoint-based ambient occlusion. IEEE Comput. Graph. Appl. 28, 44–51 (2008)Google Scholar
  10. 10.
    Harvda, J., Charvát, F.: Quantification method of classification processes. Concept of structural \(\alpha \)-entropy. Kybernetika 3, 30–35 (1967)Google Scholar
  11. 11.
    Iones, A., Krupkin, A., Sbert, M., Zhukov, S.: Fast, realistic lighting for video games. IEEE Comput. Graph. Appl. 23(3), 54–64 (2003)CrossRefGoogle Scholar
  12. 12.
    Landis, H.: RenderMan in production. In: Course notes of ACM SIGGRAPH (2002)Google Scholar
  13. 13.
    Langer, M., Bülthoff, H.: Depth discrimination from shading under diffuse lighting. Perception 29(6), 649–660 (2000)CrossRefGoogle Scholar
  14. 14.
    Méndez-Feliu, A., Sbert, M.: From obscurances to ambient occlusion: A survey. Vis. Comp. 25, 181–196 (2009)CrossRefGoogle Scholar
  15. 15.
    Palmer, S., Rosch, E., Chase, P.: Canonical perspective and the perception of objects. Atten. Perform. IX, 135–151 (1981)Google Scholar
  16. 16.
    Sokolov, D., Plemenos, D., Tamine, K.: Methods and data structures for virtual world exploration. Vis. Comput. 22(7), 506–516 (2006)CrossRefGoogle Scholar
  17. 17.
    Taneja, I.J.: Bivariate measures of type \(\alpha \) and their applications. Tamkang J. Math. 19(3), 63–74 (1988)MathSciNetMATHGoogle Scholar
  18. 18.
    Tarr, M., Bülthoff, H., Zabinski, M., Blanz, V.: To what extent do unique parts influence recognition across changes in viewpoint? Psychol. Sci. 8(4), 282–289 (1997)CrossRefGoogle Scholar
  19. 19.
    Thompson, W., Fleming, R., Creem-Regehr, S., Stefanucci, J.K.: Visual Perception from a Computer Graphics Perspective. A K Peters/CRC Press, Boca Raton (2011)Google Scholar
  20. 20.
    Tsallis, C.: Possible generalization of Boltzmann-Gibbs statistics. J. Stat. Phys. 52(1/2), 479–487 (1988)MathSciNetMATHCrossRefGoogle Scholar
  21. 21.
    Tsallis, C.: Generalized entropy-based criterion for consistent testing. Phys. Rev. E 58, 1442–1445 (1998)CrossRefGoogle Scholar
  22. 22.
    Vázquez, P.P., Feixas, M., Sbert, M., Heidrich, W.: Viewpoint selection using viewpoint entropy. In: Proceedings of Vision, Modeling, and Visualization 2001, pp. 273–280 (2001)Google Scholar
  23. 23.
    Viola, I., Feixas, M., Sbert, M., Gröller, M.E.: Importance-driven focus of attention. IEEE Trans. Vis. Comput. Graph. 12(5), 933–940 (2006)CrossRefGoogle Scholar
  24. 24.
    Yeung, R.W.: Information Theory and Network Coding. Springer, Berlin (2008)MATHGoogle Scholar
  25. 25.
    Zhukov, S., Iones, A., Kronin, G.: An ambient light illumination model. In: Drettakis, G., Max, N. (eds.) Rendering Techniques ’98. Eurographics, pp. 45–56. Springer, New York (1998)Google Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  • Xavier Bonaventura
    • 1
  • Miquel Feixas
    • 1
  • Mateu Sbert
    • 1
  1. 1.University of GironaGironaSpain

Personalised recommendations