Junction and Corner Detection Through the Extraction and Analysis of Line Segments

  • Christian Perwass
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3322)


An algorithm is presented that analyzes the edge structure in images locally, using a geometric approach. A local edge structure that can be interpreted as a corner or a junction is assumed to be representable by a set of line segments. In a first step a segmentation of the local edge structure into line segments is evaluated. This leads to a graph model of the local edge structure, which can be analyzed further using a combinatorial method. The result is a classification as corner or junction together with the absolute orientation and internal structure, like the opening angle of a corner, or the angles between the legs of a junction. Results on synthetic and real data are given.


Line Segment Intersection Point Image Patch Edge Point Image Gradient 
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.
    Baker, S., Nayar, S.K., Murase, H.: Parametric feature detection. IJCV 27(1), 27–50 (1998)CrossRefGoogle Scholar
  2. 2.
    Bookstein, F.L.: Fitting conic sections to scattered data. Comp. Graph. Image Proc. 9, 56–71 (1979)CrossRefGoogle Scholar
  3. 3.
    Canny, J.: A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 8(6) (November 1986)Google Scholar
  4. 4.
    Cazorla, M.A., Escolano, F., Rizo, R., Gallardo, D.: Bayesian models for finding and grouping junctions. In: Hancock, E.R., Pelillo, M. (eds.) EMMCVPR 1999. LNCS, vol. 1654, pp. 70–82. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  5. 5.
    Felsberg, M., Sommer, G.: The monogenic signal. IEEE Transactions on Signal Processing 49(12), 3136–3144 (2001)CrossRefMathSciNetGoogle Scholar
  6. 6.
    Felsberg, M., Sommer, G.: Image features based on a new approach to 2D rotation invariant quadrature filters. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 369–383. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  7. 7.
    Förstner, W.: A feature based correspondence algorithm for image matching. Intl. Arch. of Photogrammetry and Remote Sensing 26, 150–166 (1986)Google Scholar
  8. 8.
    Förstner, W.: A framework for low level feature extraction. In: Eklundh, J.-O. (ed.) ECCV 1994. LNCS, vol. 801, pp. 383–394. Springer, Heidelberg (1994)CrossRefGoogle Scholar
  9. 9.
    Granlund, G.H., Moe, A.: Unrestricted recognition of 3-D objects using multi-level triplet invariants. In: Proceedings of the Cognitive Vision Workshop, Zürich, Switzerland (September 2002),
  10. 10.
    Harris, C.G., Stevens, M.J.: A combined corner and edge detector. In: Proc. of 4th Alvey Vision Conference (1988)Google Scholar
  11. 11.
    Köthe, U.: Edge and junction detection with an improved structure tensor. In: Michaelis, B., Krell, G. (eds.) DAGM 2003. LNCS, vol. 2781, pp. 25–32. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  12. 12.
    Lowe, D.G.: Local feature view clustering for 3d object recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 682–688 (2001)Google Scholar
  13. 13.
    Mokhtarian, F., Suomela, R.: Curvature scale space for robust image corner detection. In: Proc. International Conference on Pattern Recognition, pp. 1819–1821 (1998)Google Scholar
  14. 14.
    Perwass, C.: Analysis of local image structure using intersections of conics. Technical Report Number 0403, Christian-Albrechts-Universität zu Kiel, Institut für Informatik und Praktische Mathematik (July 2004)Google Scholar
  15. 15.
    Shpitalni, M., Lipson, H.: Classification of sketch strokes and corner detection using conic sections and adaptive clustering. Trans. of ASME J. of Mechanical Design 119(2), 131–135 (1997)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Christian Perwass
    • 1
  1. 1.Institut für Informatik und Praktische MathematikChristian-Albrechts-Universität zu KielKielGermany

Personalised recommendations