On Pencils of Tangent Planes and the Recognition of Smooth 3D Shapes from Silhouettes

  • Svetlana Lazebnik
  • Amit Sethi
  • Cordelia Schmid
  • David Kriegman
  • Jean Ponce
  • Martial Hebert
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2352)


This paper presents a geometric approach to recognizing smooth objects from their outlines. We define a signature function that associates feature vectors with objects and baselines connecting pairs of possible viewpoints. Feature vectors, which can be projective, affine, or Euclidean, are computed using the planes that pass through a fixed baseline and are also tangent to the object’s surface. In the proposed framework, matching a test outline to a set of training outlines is equivalent to finding intersections in feature space between the images of the training and the test signature functions. The paper presents experimental results for the case of internally calibrated perspective cameras, where the feature vectors are angles between epipolar tangent planes.


Feature Vector Feature Space Image Plane Signature Function Tangent Plane 
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.
    R. Basri and S. Ullman, “The Alignment of Objects with Smooth Surfaces”, Proc. of Int. Conf. on Computer Vision, 1988, pp. 482–488.Google Scholar
  2. 2.
    S. Belongie, J. Malik and J. Puzicha, “Shape Matching and Object Recognition Using Shape Contexts”, to appear, IEEE Trans. on Pattern Analysis and Machine Intelligence, 24(3), 2002.Google Scholar
  3. 3.
    S. Carlsson, “Order Structure, Correspondence, and Shape Based Categories”, Proc. of Int. Workshop on Shape, Contour and Grouping, 1999, pp. 58–71.Google Scholar
  4. 4.
    R. Cipolla, K. Astrom and P.J. Giblin, “Motion from the Frontier of Curved Surfaces”, Proc. of IEEE Int. Conf. on Computer Vision, 1995, pp. 269–275.Google Scholar
  5. 5.
    V. Guillemin and A. Pollack, Differential Topology, Prentice Hall, Englewood Cliffs, New Jersey, 1974.zbMATHGoogle Scholar
  6. 6.
    R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press, Cambridge, 2000.zbMATHGoogle Scholar
  7. 7.
    D. Jacobs, P. Belhumeur and I. Jermyn, “Judging Whether Multiple Silhouettes Can Come from the Same Object”, to appear, Proc. of the 4th Int. Workshop on Visual Form, 2001.Google Scholar
  8. 8.
    J. Porrill and S. Pollard, “Curve Matching and Stereo Calibration”, Image and Vision Computing, 9(1), 1991, pp. 45–50.CrossRefGoogle Scholar
  9. 9.
    D. Renaudie, D. Kriegman and J. Ponce, “Duals, Invariants, and the Recognition of Smooth Objects from their Occluding Contour”, Proc. of Eur. Conf. on Computer Vision, 2000, pp. 784–798.Google Scholar
  10. 10.
    C. Schmid, “Constructing models for content-based image retrieval”, Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, 2001.Google Scholar
  11. 11.
    H. Schneiderman and T. Kanade, “A Statistical Method of 3D Object Detection Applied to Faces and Cars“, Proc. of IEEE Conf. on Computer Vision and Pattern Recognition 2000, pp. 746–751.Google Scholar
  12. 12.
    M. Weber, M. Welling and P. Perona, “Towards Automatic Discovery of Object Categories“, Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, 2000.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Svetlana Lazebnik
    • 1
  • Amit Sethi
    • 1
  • Cordelia Schmid
    • 2
  • David Kriegman
    • 1
  • Jean Ponce
    • 1
  • Martial Hebert
    • 3
  1. 1.Beckman Institute for Advanced Science and TechnologyUniversity of Illinois at Urbana-ChampaignUrbanaUSA
  2. 2.INRIA Rhône-AlpesMontbonnotFrance
  3. 3.Robotics InstituteCarnegie Mellon UniversityPittsburghUSA

Personalised recommendations