Skip to main content
SpringerLink
Log in

Primitive-Based Shape Modeling and Recognition

  • Chapter
Visual Form

Abstract

We present an approach to the recovery and recognition of 3-D objects from a single 2-D image. Given a recognition domain consisting of a database of objects, we select a set of object-centered 3-D volumetric modeling primitives that can be used to construct the objects. Next, we take the set of primitives and generate a hierarchical aspect representation based on their projected surfaces; conditional probabilities capture the ambiguity of mappings between levels of the hierarchy. From a region segmentation of the input image, we present a novel formulation of the recovery problem based on grouping the regions into aspects. No domain dependent heuristics are used; we exploit only the probabilities inherent in the aspect hierarchy. Once the aspects are recovered, we use the aspect hierarchy to infer a set of volumetric primitives and their connectivity. Subgraphs of the resulting graph, in which nodes represent 3-D primitives and arcs represent primitive connections, are used as indices into the object database. Object verification consists of a topological verification of the recovered graph rather than a geometrical verification of image features.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 169.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 219.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bergevin, Robert and Martin Levine, “Generic Object Recognition: Building Coarse 3D Descriptions from Line Drawings”, Proceedings, IEEE Workshop on Interpretation of 3D Scenes, Austin, TX, November 1989, pp 68-74.

    Google Scholar 

  2. Besl, Paul J. and Ramesh C. Jain, “Segmentation Through Variable-Order Surface Fitting”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 10, No. 2, March 1988, pp 167–192.

    Article  Google Scholar 

  3. Biederman, Irving, “Human Image Understanding: Recent Research and a Theory”, Computer Vision, Graphics, and Image Processing, Vol. 32, 1985, pp 29–73.

    Article  Google Scholar 

  4. Binford, Thomas O., “Visual Perception by Computer”, Proceedings, IEEE Conference on Systems and Control, Miami, FL, 1971.

    Google Scholar 

  5. Brooks, Rodney Allen, “Model-Based 3-D Interpretations of 2-D Images”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 5, No. 2, March 1983, pp 140–150.

    Article  Google Scholar 

  6. Canny, John, “A Computational Approach to Edge Detection”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 8, No. 6, November 1986, pp 679–698.

    Article  Google Scholar 

  7. Chakravarty, Indranil and Herbert Freeman, “Characteristic Views as a Basis for Three-Dimensional Object Recognition”, Proceedings, SPIE Conference on Robot Vision, Arlington VA, May 6–7, 1982, pp 37-45.

    Google Scholar 

  8. Dickinson, Sven J., Alex P. Pentland, and Azriel Rosenfeld, “A Representation for Qualitative 3-D Object Recognition Integrating Object-Centered and Viewer-Centered Models”, in: K.N. Leibovic (ed.), Vision: A Convergence of Disciplines, Springer Verlag, New York, 1990.

    Google Scholar 

  9. Dickinson, Sven J., Alex P. Pentland, and Azriel Rosenfeld, “Qualitative 3-D Shape Recovery Using Distributed Aspect Matching”, Technical Report CAR-TR-453, Center for Automation Research, University of Maryland, June, 1990.

    Google Scholar 

  10. Dolan, John and Richard Weiss, “Perceptual Grouping of Curved Lines”, Proceedings, DARPA Image Understanding Workshop, Palo Alto, CA, 1989, pp 1135-1145.

    Google Scholar 

  11. Eggert, David and Kevin Bowyer, “Computing the Orthographic Projection Aspect Graph of Solids of Revolution”, Proceedings, IEEE Workshop on Interpretation of 3D Scenes, Austin, TX, 1989, pp 102-108.

    Google Scholar 

  12. Fan, T.J., G. Medioni, and R. Nevatia, “Recognizing 3-D Objects using Surface Descriptions”, Proceedings, Second International Conference on Computer Vision, Tampa, FL, 1988, pp 474-481.

    Google Scholar 

  13. Fischler, M.A. and R.C. Bolles, “Perceptual Organization and Curve Partitioning”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 8, No. 1, January 1986, pp 100–105.

    Article  Google Scholar 

  14. Gigus, Ziv and Jitendra Malik, “Computing the Aspect Graph for Line Drawings of Polyhedral Objects”, Technical Report No. UCB/CSD 88/402, Computer Science Division (EECS), University of California, Berkeley, February, 1988.

    Google Scholar 

  15. Gigus, Ziv, John Canny, and Raimund Seidel, “Efficiently Computing and Representing Aspect Graphs of Polyhedral Objects”, Technical Report No. UCB/CSD 88/432, Computer Science Division (EECS), University of California, Berkeley, August, 1988.

    Google Scholar 

  16. Grimson, W. Eric L., “The Effect of Indexing on the Complexity of Object Recognition”, Memo No. 1226, Artificial Intelligence Laboratory, Massachusetts Institute of Technology, April, 1990.

    Google Scholar 

  17. Haralick, Robert M. and Linda Shapiro, “Image Segmentation Techniques”, Computer Vision, Graphics, and Image Processing, Vol. 29, 1985, pp 100–132.

    Article  Google Scholar 

  18. Huttenlocher, Daniel P. and Shimon Ullman, “Object Recognition Using Alignment”, Proceedings, First International Conference on Computer Vision, London, UK, 1987, pp 102-111.

    Google Scholar 

  19. Ikeuchi, Katsushi and Takeo Kanade, “Automatic Generation of Object Recognition Programs”, Proceedings of the IEEE, Vol. 76, No. 8, August 1988, pp 1016–1035.

    Article  Google Scholar 

  20. Koenderink, J. J. and A. J. van Doorn, “The Internal Representation of Solid Shape with Respect to Vision”, Biological Cybernetics, Vol. 32, 1979, pp 211–216.

    Article  MATH  Google Scholar 

  21. Lamdan, Yehezkel, Jacob T. Schwartz and Haim J. Wolfson, “On Recognition of 3-D Objects from 2-D Images”, Proceedings, IEEE International Conference on Robotics and Automation, Philadelphia, PA, 1988, pp 1407-1413.

    Google Scholar 

  22. Liao, Y., “A Two-Stage Method of Fitting Conic Arcs and Straight-Line Segments to Digitized Contours”, Proceedings, Pattern Recognition and Image Processing Conference, Dallas, TX, 1981, pp 224-229.

    Google Scholar 

  23. Lowe, David G., Perceptual Organization and Visual Recognition, Kluwer Academic Publishers, Norwell, MA, 1985.

    Book  Google Scholar 

  24. Meer, Peter, Doron Mintz and Azriel Rosenfeld, “Least Median of Squares Based Robust Analysis of Image Structure”, Proceedings, DARPA Image Understanding Workshop, Pittsburgh, PA, 1990, pp 231-254.

    Google Scholar 

  25. Mohan, Rakesh and Ramakant Nevatia, “Perceptual Organization for Segmentation and Description”, Proceedings, DARPA Image Understanding Workshop, Palo Alto, CA, 1989, pp 415-424.

    Google Scholar 

  26. Nilsson, Nils J., Principles of Artificial Intelligence, Chapter 2, Morgan Kaufmann Publishers, Inc., Los Altos, CA, 1980.

    MATH  Google Scholar 

  27. Pentland, Alex P., “Perceptual Organization and the Representation of Natural Form”, Artificial Intelligence, Vol. 28, 1986, pp 293–331.

    Article  MathSciNet  Google Scholar 

  28. Ramer, U., “An Iterative Procedure for the Polygonal Approximation of Plane Curves”, Computer Graphics and Image Processing, Vol. 1, 1972, pp 244–256.

    Article  Google Scholar 

  29. Roberts, L. G., “Machine Perception of Three-Dimensional Solids”, in: J.T. Tippett et al. (Eds.), Optical and Electro-Optical Information Processing, MIT Press, Cambridge, MA, 1965, pp 159–197.

    Google Scholar 

  30. Rosenfeld, Azriel, “Recognizing Unexpected Objects: A Proposed Approach”, Proceedings, DARPA Image Understanding Workshop, Los Angeles, CA, 1987, pp 620-627.

    Google Scholar 

  31. Saint-Marc, Philippe and Gerard Medioni, “Adaptive Smoothing for Feature Extraction”, Proceedings, 1988 DARPA Image Understanding Workshop, Cambridge, MA, 1988, pp 1100-1113.

    Google Scholar 

  32. Shapiro, Linda G. and Haiyuan Lu, “Accumulator-Based Inexact Matching using Relational Summaries”, Machine Vision and Applications, Vol. 3, 1990, pp 143–158.

    Article  Google Scholar 

  33. Sripradisvarakul, Thawach and Ramesh Jain, “Generating Aspect Graphs for Curved Objects”, Proceedings, IEEE Workshop on Interpretation of 3D Scenes, Austin, TX, 1989, pp 109-115.

    Google Scholar 

  34. Stark, Louise, David Eggert, and Kevin Bowyer, “Aspect Graphs and Nonlinear Optimization in 3-D Object Recognition”, Proceedings, IEEE Second International Conference on Computer Vision, Tampa, FL, 1988, pp 501-507.

    Google Scholar 

  35. Stewman, John and Kevin Bowyer, “Creating the Perspective Projection Aspect Graph of Polyhedral Objects”, Proceedings, IEEE Second International Conference on Computer Vision, Tampa, FL, 1988, pp 494-500.

    Google Scholar 

  36. Stewman, John and Kevin Bowyer, “Direct Construction of the Perspective Projection Aspect Graph of Convex Polyhedra”, Computer Vision, Graphics, and Image Processing, Vol. 51, 1990, pp 20–37.

    Article  Google Scholar 

  37. Terzopoulos, Demetri and Dimitri Metaxas, “Dynamic 3D Models with Local and Global Deformations: Deformable Superquadrics”, Proceedings, IEEE Third International Conference on Computer Vision, Osaka, Japan, 1990, pp 606-615.

    Google Scholar 

  38. Thompson, D.W. and J.L. Mundy, “Model-Directed Object Recognition on the Connection Machine”, Proceedings, DARPA Image Understanding Workshop, Los Angeles, CA, 1987, pp 93-106.

    Google Scholar 

  39. Witkin, Andrew P., and Tenenbaum, Jay M., “On the Role of Structure in Vision”, in: Jacob Beck, Barbara Hope, and Azriel Rosenfeld (eds.), Human and Machine Vision, Academic Press, NY, 1983, pp 481–543.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Center for Automation Research, University of Maryland, College Park, MD, 20742-3411, USA

    Sven J. Dickinson & Azriel Rosenfeld

  2. Vision and Modeling Group, Media Laboratory, M.I.T., Cambridge, MA, 02139, USA

    Alex P. Pentland

Authors
  1. Sven J. Dickinson
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Azriel Rosenfeld
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Alex P. Pentland
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Istituto di Cibernetica, Consiglio Nazionale delle Ricerche, Naples, Italy

    Carlo Arcelli  & Gabriella Sanniti di Baja  & 

  2. Dipartimento di Informatica e Sistemistica, Università di Napoli Federico II, Naples, Italy

    Luigi P. Cordella

Rights and permissions

Reprints and permissions

Copyright information

© 1992 Springer Science+Business Media New York

About this chapter

Cite this chapter

Dickinson, S.J., Rosenfeld, A., Pentland, A.P. (1992). Primitive-Based Shape Modeling and Recognition. In: Arcelli, C., Cordella, L.P., di Baja, G.S. (eds) Visual Form. Springer, Boston, MA. https://doi.org/10.1007/978-1-4899-0715-8_22

Download citation

  • DOI: https://doi.org/10.1007/978-1-4899-0715-8_22

  • Publisher Name: Springer, Boston, MA

  • Print ISBN: 978-1-4899-0717-2

  • Online ISBN: 978-1-4899-0715-8

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation