Junction classification by multiple orientation detection

  • M. Michaelis
  • G. Sommer
Image Features
Part of the Lecture Notes in Computer Science book series (LNCS, volume 800)


Junctions of lines or edges are important visual cues in various fields of computer vision. They are characterized by the existence of more than one orientation at one single point, the so called keypoint. In this work we investigate the performance of highly orientation selective functions to detect multiple orientations and to characterize junctions. A quadrature pair of functions is used to detect lines as well as edges and to distinguish between them. An associated one-sided function with an angular periodicity of 360° can distinguish between terminating and non-terminating lines and edges which constitute the junctions. To calculate the response of these functions in a continuum of orientations and scales a method is used that was introduced recently by P. Perona [8].


Basis Function Orientation Selectivity Line Junction Quadrature Pair Intrinsic Scale 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    M.T. Andersson, Controllable multidimensional filters and models in low level computer vision, PhD Thesis, Linköping University, S-58183 Linköping, Sweden, 1992, Diss. No. 282, ISBN 91-7870-981-4.Google Scholar
  2. 2.
    K. Brunnström, J.-O. Eklundh and T. Lindeberg, On scale and resolution in active analysis of local image structure, Image and Vision Computing 8 (1990) 289–296.Google Scholar
  3. 3.
    W.T. Freeman and E.H. Adelson, The design and use of steerable filters for image analysis, enhancement, and wavelet representation, IEEE PAMI 13 (1991) 891–906.Google Scholar
  4. 4.
    A. Guiducci, Corner characterization by differential geometry techniques, Pattern Recognition Letters 8 (1988) 311–318.Google Scholar
  5. 5.
    M. Michaelis and G. Sommer, Keypoint characterization in images, Proceedings of the SPIE 2093, in press, (1993).Google Scholar
  6. 6.
    J.A. Noble, Finding corners, Image and Vision Computing, 6 (1988) 121–128.Google Scholar
  7. 7.
    P. Perona and J. Malik, Detecting and localizing edges composed of steps, peaks and roofs, UC Berkeley, Tech. Rep. UCB/CSD 90/590 (1990).Google Scholar
  8. 8.
    P. Perona, Steerable-scalable kernels for edge detection and junction analysis, ECCV 92 (1992) 3–18.Google Scholar
  9. 9.
    K. Rohr, Recognizing corners by fitting parametric models, Int.J. of Computer Vision 9 (1992) 213–230.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • M. Michaelis
    • 1
  • G. Sommer
    • 2
  1. 1.GSF-MEDIS-InstitutOberschleißheimGermany
  2. 2.Institut für InformatikChristian-Albrechts-UniversitätKielGermany

Personalised recommendations