Advertisement

Abstraction and Generalization of 3D Structure for Recognition in Large Intra-Class Variation

  • Gowri Somanath
  • Chandra Kambhamettu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6494)

Abstract

Humans have abstract models for object classes which helps recognize previously unseen instances, despite large intra-class variations. Also objects are grouped into classes based on their purpose. Studies in cognitive science show that humans maintain abstractions and certain specific features from the instances they observe. In this paper, we address the challenging task of creating a system which can learn such canonical models in a uniform manner for different classes. Using just a few examples the system creates a canonical model (COMPAS) per class, which is used to recognize classes with large intra-class variation (chairs, benches, sofas all belong to sitting class). We propose a robust representation and automatic scheme for abstraction and generalization. We quantitatively demonstrate improved recognition and classification accuracy over state-of-art 3D shape matching/classification method and discuss advantages over rule based systems.

Keywords

Random Forest Gaussian Mixture Model Object Class Spherical Function Category Learning 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Winston, P.H.: Learning structural descriptions from examples. In: Winston, P.h. (ed.) The Psychology of Computer Vision, McGraw-Hill, New York (1975)Google Scholar
  2. 2.
    Winston, P., Binford, T., Katz, B., Lowry, M.: Learning physical descriptions from functional definitions, examples,and precedents. In: Proc. Int. Symp. Robotics Research, vol. 1. MIT Press, Cambridge (1984)Google Scholar
  3. 3.
    Connell, J.H., Brady, M.: Generating and generalizing models of visual objects. Artif. Intell. 31, 159–183 (1987)CrossRefGoogle Scholar
  4. 4.
    Brady, M., Agre, P.E., Braunegg, D.J., Connell, J.H.: The mechanics mate. In: Advances in Artificial Intelligence, pp. 79–94 (1985)Google Scholar
  5. 5.
    Minsky, M.: The society of mind, pp. 79–94 (1985)Google Scholar
  6. 6.
    Posner, M.I., Keele, S.W.: On the genesis of abstract ideas. J. Exp. Psychol. 77, 353–363 (1968)CrossRefGoogle Scholar
  7. 7.
    Reed, S.K.: Pattern recognition and categorization. Cognitive Psychology 3, 382–407 (1972)CrossRefGoogle Scholar
  8. 8.
    Smith, J.D., Paul, J.: Distinguishing prototype-based and exemplar-based processes in dot-pattern category learning. Processes in Category Learning, Journal of Experimental Psychology: Learning, Memory, and Cognition, 800–811 (2002)Google Scholar
  9. 9.
    Stark, L., Bowyer, K.: Achieving generalized object recognition through reasoning about association of function to structure. IEEE Transactions on Pattern Analysis and Machine Intelligence 13, 1097–1104 (1991)CrossRefGoogle Scholar
  10. 10.
    Stark, L., Bowyer, K.: Function-based generic recognition for multiple object categories. CVGIP: Image Understanding 59, 1–21 (1994)CrossRefGoogle Scholar
  11. 11.
    Pechuk, M., Soldea, O., Rivlin, E.: Learning function-based object classification from 3d imagery. Computer Vision and Image Understanding 110, 173–191 (2008)CrossRefGoogle Scholar
  12. 12.
    Fried, L.S., Holyoak, K.J.: Induction of category distributions: A framework for classification learning. Journal of Experimental Psychology: Learning, Memory, and Cognition 10, 234–257 (1984)Google Scholar
  13. 13.
    Rips, L.J.: Similarity, typicality, and categorization, pp. 21–59 (1989)Google Scholar
  14. 14.
    Estes, W.K.: Array models for category learning. Cognitive Psychology, 500–549 (1986)Google Scholar
  15. 15.
    Brooks, L.R.: Nonanalytic concept formation and memory for instances. In: Rosch, E., Lloyd, B.B. (eds.) Cognition and Categorization, pp. 169–211 (1978)Google Scholar
  16. 16.
    Rosch, E.: Principles of categorization. In: Rosch, E., Lloyd, B.B. (eds.) Cognition and Categorization, pp. 27–48 (1978)Google Scholar
  17. 17.
    Ashby, F.G., Alfonso-Reese, L.A., Turken, A.U., Waldron, E.M.: A neuropsychological theory of multiple systems in category learning. Psychological Review, 442–481 (1998)Google Scholar
  18. 18.
    Ashby, F.G., Ell, S.W.: The neurobiology of human category learning. Trends in Cognitive Science, 204–210 (2001)Google Scholar
  19. 19.
    Erickson, M.A., Kruschke, J.K.: Rules and exemplars in category learning. Journal of Experimental Psychology: General, 107–140 (1998)Google Scholar
  20. 20.
    Love, B.C., Medin, D.L., Gureckis, T.M.: A network model of category learning. Psychological Review, 309–332 (2004)Google Scholar
  21. 21.
    Vanpaemel, W., Storms, G.: In search of abstraction: the varying abstraction model of categorization. Psychonomic Bulletin and Review, 732–749 (2008)Google Scholar
  22. 22.
    Smith, J.D., Chapman, W.P., Redford, J.S.: Stages of category learning in monkeys (macaca mulatta) and humans (homo sapiens). Journal of Experimental Psychology: Animal Behavior Processes, 39–53 (2010)Google Scholar
  23. 23.
    Veloso, M.M., Rybski, P.E., von Hundelshausen, F.: Focus: a generalized method for object discovery for robots that observe and interact with humans. In: HRI 2006: Proceedings of the 1st ACM SIGCHI/SIGART Conference on Human-Robot Interaction, pp. 102–109. ACM, New York (2006)Google Scholar
  24. 24.
    Gupta, A., Kembhavi, A., Davis, L.S.: Observing human-object interactions: Using spatial and functional compatibility for recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 31, 1775–1789 (2009)CrossRefGoogle Scholar
  25. 25.
    Biederman, I.: Recognition-by-components: A theory of human image understanding. Psychological Review 94, 115–147 (1987)CrossRefGoogle Scholar
  26. 26.
    Shilane, P., Min, P., Kazhdan, M., Funkhouser, T.: The princeton shape benchmark. Shape Modeling International (June 2004)Google Scholar
  27. 27.
    Saupe, D., Vranic, D.V.: 3D model retrieval with spherical harmonics and moments. In: Radig, B., Florczyk, S. (eds.) DAGM 2001. LNCS, vol. 2191, pp. 392–397. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  28. 28.
    Kostelec, P.J., Rockmore, D.N.: Ffts on the rotation group. Technical report (2003)Google Scholar
  29. 29.
    Kostelec, P., Rockmore, D.: Ffts on the rotation group. Journal of Fourier Analysis and Applications 14, 145–179 (2008)MathSciNetCrossRefzbMATHGoogle Scholar
  30. 30.
    Breiman, L.: Random forests. Machine Learning, 5–32 (2001)Google Scholar
  31. 31.
    Princeton: 3d model search engine, http://shape.cs.princeton.edu/search.html
  32. 32.
    Winston, P.H.: Learning structural descriptions from examples (1970)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Gowri Somanath
    • 1
  • Chandra Kambhamettu
    • 1
  1. 1.Video/Image Modeling and Synthesis (VIMS) Lab, Department of Computer and Information SciencesUniversity of DelawareNewarkUSA

Personalised recommendations