Object representation for recognition-by-alignment

  • George Stockman
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 994)


We present an approach general enough to apply to recognition of complex rigid 3D objects from either a single intensity image or a single range image. Within the general paradigm of recognition by alignment, we address (1) definition and detection of primitives, (2) indexing to model hypotheses, (3) constructing view sphere models from sensed data, and (4) aligning model and sensed features for verification. The overall paradigm is not new, but rather fits within theory already espoused by Lowe and Ullman and many others: our position is therefore both a synthesis of and endorsement of much other work toward recognition of rigid free-form objects.


Object Representation Range Image Indexing Scheme Model Aspect Contour Segment 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    R. Bajcsy and F. Solina: Three-Dimensional Object representation Revisited. Proceedings 1st Int. Conf. on Computer Vision, (1987) 231–240Google Scholar
  2. 2.
    R. Basri and S. Ullman: The Alignment of Objects with Smooth Surfaces. Proceedings 2nd Int. Conf. on Computer Vision, (1988) 482–488Google Scholar
  3. 3.
    K. Bowyer, D. Eggert, J. Stewman, and L. Stark: Developing the Aspect Graph Representation for Use in Image Understanding. In Proc. DARPA Image Understanding Workshop, Palo Alto,(1989) 831–849Google Scholar
  4. 4.
    T. Breuel: Adaptive Model-based Indexing. In Proc. 1989 DARPA Image Understanding Workshop, (1989) 805–814Google Scholar
  5. 5.
    A. Califano and R. Mohan: Multidimensional Indexing for Recognizing Visual Shapes. IEEE T-PAMI, Vol 16., No. 4, (1994) 373–392Google Scholar
  6. 6.
    S.-W. Chen: Wing Representation for Rigid 3D Objects. In Proc. 10th IAPR, Atlantic City, NJ, (June 1990) 398–402Google Scholar
  7. 7.
    J.-L. Chen, G. Stockman, and K. Rao: Recovering and Tracking Pose of Curved 3D Objects from 2D Images. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, New York, NY, (June 1993) 233–239Google Scholar
  8. 8.
    J.-L. Chen and G. Stockman: Indexing to model aspects using invariant contour features. Computer Science Dept. Tech. Rep., Michigan State Univ., (Nov 1994)Google Scholar
  9. 9.
    J. Ponce, D. Forsyth, L. Shapiro, R. Bajcsy, D. Metaxas, M. Hebert, K. Ikeuchi, S. Sclaroff, A. Pentland, T. Binford, A. Kak, and G. Stockman: Object Representation for Object Recognition. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Seattle, WA, (June 1994) 147–152Google Scholar
  10. 10.
    S. Edelman and D. Weinshall: A Self-organizing Multiple View Representation of 3D Objects: Biological Cybernetics, Vol.64, (1991) 209–219PubMedGoogle Scholar
  11. 11.
    P. J. Flynn and A. K. Jain: BONSAI: 3D object recognition using constrained search: IEEE-T-PAMI, Vol. 13, No. 10, (Oct 1991) 1066–1075Google Scholar
  12. 12.
    C. Goad: Special Purpose Automatic Programming for 3D Model-based Vision. In Proc. DARPA Image Understanding Workshop, Arlington, VA, (1983)Google Scholar
  13. 13.
    D. D. Hoffman and W. A. Richards: Representing smooth plane curves for recognition. In Proc. AAAI, Pittsburg,PA (1982) 5–8Google Scholar
  14. 14.
    D. Huttenlocher and S. Ullman: Recognizing solid objects using alignment: Proc. DARPA Image Understanding Workshop, (April 1988) 1114–1122Google Scholar
  15. 15.
    K. Higuchi, H. Delingette, M. Hebert, and K. Ikeuchi: Merging Multiple Views Using a Spherical Representation. In Proc. IEEE 2nd CAD-Based Vision Workshop, Champion, PA (Feb 1994) 124–131Google Scholar
  16. 16.
    G. C. Lee: Scene Representation from Fused Imagery. PhD Dissertation, Michigan State Univ., (August 1992)Google Scholar
  17. 17.
    D. G. Lowe: Three-dimensional Object Recognition from Single Two-dimensional Images. Artificial Intelligence, Vol.31 No.3, (1987) 355–395Google Scholar
  18. 18.
    A. Pentland, B. Moghaddam, and T. Starner: View-Based and Modular Eigenspaces for Face Recognition. Proceedings IEEE Conf. on Computer Vision and Pattern Recognition, Seattle, WA, (June 1994) 84–91Google Scholar
  19. 19.
    P. L. Rosin: Multiscale Representation and Matching of Curves Using Codons. CVGIP: Graphical Models and Image Proc., Vol. 55, No. 4, (1993) 286–310Google Scholar
  20. 20.
    G. Stockman: Object Recognition and Localization via Pose Clustering. CVGIP, Vol. 40, (1987) 361–387Google Scholar
  21. 21.
    G. Taubin and F. Cukierman and S. Sullivan and J. Ponce and D. J. Kriegman: Parameterized Families of Polynomials for Bounded Algebraic Curve and Surface Fitting. IEEE T-PAMI, vol.16 no.3, (Mar 1994) 287–303Google Scholar
  22. 22.
    S. Ullman: An Approach to Object Recognition: Aligning Pictorial Descriptions. Technical Report AI Memo No.931, M.I.T. AI Laboratory, (1986)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • George Stockman
    • 1
  1. 1.Computer Science DepartmentMichigan State UniversityE. Lansing

Personalised recommendations