Object recognition using local geometric constraints: A robust alternative to tree-search

  • Alistair J Bray
Recognition - Matching
Part of the Lecture Notes in Computer Science book series (LNCS, volume 427)


A new algorithm is presented for recognising 3D polyhedral objects in a 2D segmented image using local geometric constraints between 2D line segments. Results demonstrate the success of the algorithm at coping with poorly segmented images that would cause substantial problems for many current algorithms. The algorithm adapts to use with either 3D line data or 2D polygonal objects; either case increases its efficiency. The conventional approach of searching an interpretation tree and pruning it using local constraints is discarded; the new approach accumulates the information available from the local constraints and forms match hypotheses subject to two global constraints that are enforced using the competitive paradigm. All stages of processing consist of many extremely simple and intrinsically parallel operations. This parallelism means that the algorithm is potentially very fast, and contributes to its robustness. It also means that the computation can be guaranteed to complete after a known time.


Model Line Image Segment Maximal Clique Local Constraint Image Line 
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.


  1. [1]
    Grimson W E L and Lozano-Perez T. Model-based recognition and localisation from sparse range or tactile data. International Journal of Robotics Research, 3(3):3–35, 1984.Google Scholar
  2. [2]
    Grimson W E L. The combinatorics of object recognition in cluttered environments using constrained search. Second International Conference on Computer Vision, IEEE, pages 218–227, 1988.Google Scholar
  3. [3]
    Grimson W E L. On the recognition of curved objects. IEEE Pattern Analysis and Machine Intelligence PAMI, 11(6):632–643, 1989.Google Scholar
  4. [4]
    Goad C. Special purpose automatic programming for 3d model-based vision. Proc. Image Understanding Workshop, Virginia, USA, pages 94–104, 1983.Google Scholar
  5. [5]
    Goad C. Fast 3d model-based vision. In Pentland A P, editor, From Pixels to Predicates, pages 371–391. 1984.Google Scholar
  6. [6]
    Bray A J. Tracking objects using image disparities. Proceedings of the 6th Alvey Vision Conference, Reading, 1989.Google Scholar
  7. [7]
    Bolles R C. Robust feature matching through maximal cliques. Proc. SPIE Technical Symposium on Imaging and Assembly, April, 1979.Google Scholar
  8. [8]
    Bolles R C and Cain RA. Recognizing and locating partially visible objects, the local-feature-focus method. International Journal of Robotics Research, 1(3):57–82, 1982.Google Scholar
  9. [9]
    Johnston H C. Cliques of a graph-large or small. Draft, Queen's University of Belfast, 1975.Google Scholar
  10. [10]
    Lowe D G.Perceptual Organisation and Visual Recognition. PhD thesis, Stanford University, Dept. of Computer Science, 1984.Google Scholar
  11. [11]
    Lowe D G.Perceptual Organisation and Visual Recognition. Boston: Kluwer, 1985.Google Scholar
  12. [12]
    Lowe D G. Three-dimensional object recognition from two-dimensional images. Artificial Intelligence, 31(3), 1987.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1990

Authors and Affiliations

  • Alistair J Bray
    • 1
  1. 1.University of SussexUK

Personalised recommendations