Skip to main content
SpringerLink
Log in

A unified framework for salient curves, regions, and junctions inference

  • Session S1B: Segmentation and Grouping
  • Conference paper
  • First Online:
Computer Vision — ACCV'98 (ACCV 1998)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1352))

Included in the following conference series:

  • 2681 Accesses

Abstract

We present a unified computational framework to generate descriptions in terms of regions, curves, and labelled junctions, from sparse, noisy, binary data in 2-D. Each input site can be a point, a point with an associated tangent direction, a point with an associated tangent vector, or any combination of the above. The methodology is grounded on two elements: tensor calculus for representation, and non-linear voting for communication. Each input site communicates its information (a tensor) to its neighborhood through a predefined (tensor) field, and therefore casts a (tensor) vote. Each site collects all the votes cast at its location and encodes them into a new tensor. A local, parallel routine then simultaneously detects junctions, curves and region boundaries. The proposed approach is non-iterative, and the only free parameter is the size of the neighborhood, related to the scale. We illustrate the approach with results on a variety of images, then outline further applications.

This research was supported by NSF Grant under award No. IRI-9024369.

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

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. N. Ahuja and M. Tuceryan, “Extraction of early perceptual structure in dot patterns: integrating region, boundary, and component Gestalt”, Computer Vision, Graphics and Image Processing, vol. 48, 1989, pp. 304–356.

    Google Scholar 

  2. J. Dolan and R. Weiss, “Perceptual Grouping of Curved Lines”, Proc. Image Understanding Workshop, 1989, pp. 1135–1145.

    Google Scholar 

  3. G.H. Granlund and Knutsson, Signal Processing for Computer Vision, Kluwer Academic Publishers, 1995.

    Google Scholar 

  4. G. Guy and G. Medioni, “Inferring Global Perceptual Contours from Local Features”, Int. J. of Computer Vision, vol. 20, no. 1/2, 1996, pp. 113–133.

    Google Scholar 

  5. G. Guy and G. Medioni, “Inference of Surfaces, 3D Curves and Junctions from Sparse 3-D Data”, Proc. IEEE Symposium on Computer Vision, Coral Gable, 1995, pp. 599–604.

    Google Scholar 

  6. G. Guy, Inference of Multiple Curves and Surfaces from Sparse Data, Ph.D. dissertation, Technical Report IRIS-96-345, Institute for Robotics and Intelligent Systems, University of Southern California.

    Google Scholar 

  7. F. Heitger and R. von der Heydt, “A Computational Model of Neural Contour Processing: Figure-Ground Segregation and Illusory Contours”, Proc. Int. Conf Computer Vision, 1993, pp. 32–40.

    Google Scholar 

  8. M.S. Lee and G. Medioni, “Inferred Descriptions in terms of Curves, Regions, and Junctions from Sparse, Noisy Binary Data”, Proc. Int. Workshop on Visual Form, Capri, Italy, May 1997, to appear.

    Google Scholar 

  9. W.E. Lorensen and H.E. Cline, “Marching Cubes: A High Resolution 3-D Surface Reconstruction Algorithm”, Computer Graphics, vol. 21, no. 4, 1987.

    Google Scholar 

  10. P. Parent and S.W. Zucker, “Trace Inference, Curvature Consistency, and Curve Detection”, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no.8, 1989, pp. 823–839.

    Google Scholar 

  11. A. Sha'ashua and S. Ullman, “Structural Saliency: the Detection of Globally Salient Structures using a Locally Connected Network”, Proc. Int. Conf. on Computer Vision, 1988, pp.321–327.

    Google Scholar 

  12. L.R. Williams and D. Jacobs, “Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience”, Proc. Int. Conf. Computer Vision, 1995,pp. 408–415.

    Google Scholar 

  13. S.W. Zucker and R.A. Hummel, “Toward a Low-Level Description of Dot Clusters: Labeling Edge, Interior, and Noise Points”, Computer Vision, Graphics, and Image Processing, vol. 9, no.3, 1979, pp.213–234

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute for Robotics and Intelligent Systems, University of Southern California, 90230, Los Angeles, CA, USA

    Mi-Suen Lee & Gérard Medioni

Authors
  1. Mi-Suen Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Gérard Medioni
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Roland Chin Ting-Chuen Pong

Rights and permissions

Reprints and permissions

Copyright information

© 1997 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Lee, MS., Medioni, G. (1997). A unified framework for salient curves, regions, and junctions inference. In: Chin, R., Pong, TC. (eds) Computer Vision — ACCV'98. ACCV 1998. Lecture Notes in Computer Science, vol 1352. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63931-4_232

Download citation

  • DOI: https://doi.org/10.1007/3-540-63931-4_232

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-63931-2

  • Online ISBN: 978-3-540-69670-4

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation