The challenge of generic object recognition

  • Mourad Zerroug
  • Gérard Medioni
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 994)


We discuss the issues and challenges in the development of generic object recognition systems. We argue that high-level, volumetric part-based, descriptions are essential if we want to recognize objects which are similar but not identical to pre-stored models, under wide viewing conditions, and to automatically learn new models and add them to our knowledge base.We discuss the representation scheme and its relationships to the description extraction, recognition and learning processes. We then describe the difficulties in obtaining such descriptions from images and outline steps for robust and efficient implementations. We also demonstrate the viability of the arguments by reporting on recent progress.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bergevin, R., Levine, M.D.: Generic Object Recognition: Building and Matching Coarse Descriptions from Line Drawings. IEEE Transactions PAMI 15 (1993) 19–36Google Scholar
  2. 2.
    Biederman, I.: Recognition by Components: A Theory of Human Image Understanding. Psychological Review, 94 (1987) 115–147PubMedGoogle Scholar
  3. 3.
    Binford, T.O.: Visual Perception by Computer. IEEE Conference on Systems and Controls (1971), Miami.Google Scholar
  4. 4.
    Binford, T.O, Levitt, T.S. and Mann, W.B.: Bayesian Inference in Model-Based Machine Vision. Proceedings of AAAI Uncertainty Workshop (1987)Google Scholar
  5. 5.
    Brooks, R.A.: Model-Based Three Dimensional Interpretation of Two Dimensional Images. IEEE Transactions PAMI 5 (1983) 140–150Google Scholar
  6. 6.
    Clowes, M.B.: On Seeing Things. Artificial Intelligence 2 (1971) 79–116CrossRefGoogle Scholar
  7. 7.
    Francois, A., Médioni, G.: Hierarchical Indexing for Generic Shape Recognition. USC-IRIS Technical Report, August 1994Google Scholar
  8. 8.
    Grimson, W.E.L.: Object Recognition by Computer: The Role of Geometric Constraints. MIT Press, Cambridge, MA 1990Google Scholar
  9. 9.
    Guy, G., Médioni, G.: Inferring global perceptual contours from local features. Proceedings of the CVPR(1993)Google Scholar
  10. 10.
    Lowe, D.G.: Perceptual Organization and Visual Recognition. Kluwer Academic Publishers, Hingham, MA. 1985Google Scholar
  11. 11.
    Mackworth, A.K.: Intrepreting Pictures of Polyhedral Scenes. Artificial Intelligence 4 (1973) 121–137Google Scholar
  12. 12.
    Marr, D.: Vision W.H. Freeman and Co. Publishers, 1981Google Scholar
  13. 13.
    Mundy, J.L., Zisserman, A. editors.: Geometric Invariance in Computer Vision. MIT Press, 1992Google Scholar
  14. 14.
    Mundy, J.L., Huang, C., Liu, J., Hoffman. W., Forsyth, D.A., Rothwell, C.A., Zisserman, A., Utcke, S., and Bournez, O.: MORSE: A 3-D object recognition system based on geometric invariants. Proceedings of Image Understanding Workshop (1994) 1393–1402Google Scholar
  15. 15.
    Nevada, R. and Binford, T.O.: Description and Recognition of Complex Curved Objects. Artificial Intelligence 8 (1977) 77–98Google Scholar
  16. 16.
    Pentland, A.: Recognition by Parts. Proceedings of ICCV (1987) 612–620Google Scholar
  17. 17.
    Ponce, J., Chelberg, D. and Mann, W.B.: Invariant Properties of Straight Homogeneous Generalized Cylinders and their Contours. IEEE Transactions PAMI 11 (1989) 951–966Google Scholar
  18. 18.
    Rivlin, E., Dickinson, S.J. and Rosenfeld, A.: Recognition by Functional Parts. Proceedings of Image Understanding Workshop (1994) 1531–1539Google Scholar
  19. 19.
    Rom, H. and Médioni, G.: Hierarchical Part Decomposition and Axial Shape Description. IEEE Transactions PAMI, 13 (1993) 973–981Google Scholar
  20. 20.
    Sato, H. and Binford, T.O.: Finding and Recovering SHGC Objects in an Edge Image. Computer Vision Graphics and Image Processing 57 (1993) 346–356Google Scholar
  21. 21.
    Stark, L. and Bowyer, K.: Achieving generalized object recognition through reasoning about association of function to structure. IEEE Transactions PAMI 13 (1991) 1097–1104Google Scholar
  22. 22.
    Ulupinar, F. and Nevatia, R.: Recovering Shape from Contour for Constant Cross Section Generalized Cylinders Proceedings of CVPR (1991) 674–676Google Scholar
  23. 23.
    Zerroug, M. and Nevatia, R.: Quasi-invariant Properties and 3-D Shape Recovery of Non-Straight, Non-Constant Generalized Cylinders. In Proceedings of CVPR (1993) 96–103Google Scholar
  24. 24.
    Zerroug, M. and Nevatia, R.: From an Intensity Image to 3-D Segmented Descriptions. Proceedings of the ICPR (1994)Google Scholar
  25. 25.
    Zerroug, M. and Nevatia, R.: Using invariance and quasi-invariance for the segmentation and recovery of curved objects. Applications of Geometric Invariance in Computer Vision, LNCS 825, Springer-Verlag (1994)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Mourad Zerroug
    • 1
  • Gérard Medioni
    • 1
  1. 1.Institute for Robotics and Intelligent SystemsUniversity of Southern CaliforniaLos Angeles

Personalised recommendations