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

  • Mi-Suen Lee
  • Gérard Medioni
Session S1B: Segmentation and Grouping

DOI: 10.1007/3-540-63931-4_232

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

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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag 1997

Authors and Affiliations

  • Mi-Suen Lee
    • 1
  • Gérard Medioni
    • 1
  1. 1.Institute for Robotics and Intelligent SystemsUniversity of Southern CaliforniaLos AngelesUSA

Personalised recommendations