Multi-step procedures for the localization of 2D and 3D point landmarks and automatic ROI size selection

  • Sönke Frantz
  • Karl Rohr
  • H. Siegfried Stiehl
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1406)


In this contribution, we are concerned with the detection and refined localization of 3D point landmarks. We propose multi-step differential procedures for subvoxel localization of 3D point landmarks. Moreover, we address the problem of choosing an optimal size for a region-of-interest (ROI) around point landmarks. That is, to reliably localize the landmark position, on the one hand, as much as possible image information about the landmark should be incorporated. On the other hand, the ROI should be restricted such that other structures do not interfere.

The multi-step procedures are generalizations of an existing two-step procedure for subpixel localization of 2D point landmarks. This two-step procedure combines landmark detection by applying a differential operator with refined localization through a differential edge intersection approach. In this paper, we investigate the localization performance of this two-step procedure for an analytical model of a Gaussian blurred L-corner. The results motivate the use of an analogous procedure for 3D point landmark localization. We generalize the edge intersection approach to 3D and combine it with 3D detection operators to obtain multi-step procedures for subvoxel localization of 3D point landmarks. The multi-step procedures are experimentally tested for 3D synthetic images and 3D MR images of the human head. We also propose an approach to automatically select an optimal ROI size. This approach exploits the uncertainty of the position estimate resulting from the edge intersection approach. We present first promising results for a real 2D image with different types of corners as well as for anatomical brain landmarks in 2D slices of a 3D MR image.


Human Head Detection Operator Position Estimate Observation Window Point Landmark 
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.
    P.R. Beaudet. Rotationally invariant image operators. In Proc. International Conference on Pattern Recognition, pages 579–583, Kyoto, Japan, 1978.Google Scholar
  2. 2.
    W. Beil, K. Rohr, and H.S. Stiehl. Investigation of Approaches for the Localization of Anatomical Landmarks in 3D Medical Images. In H.U. Lemke, M.W. Vannier, and K. Inamura, editors, Proc. Computer Assisted Radiology and Surgery, pages 265–270, Berlin, Germany, 1997. Elsevier Amsterdam Lausanne.Google Scholar
  3. 3.
    L. Dreschler. Ermittlung markanter Punkte auf den Bildern bewegter Objekte und Berechnung einer 3D-Beschreibung auf dieser Grundlage. Dissertation, FB Informatik, Universität Hamburg, 1981.Google Scholar
  4. 4.
    W. Förstner. A feature based algorithm for image matching. International Archives of Photogrammetry and Remote Sensing, 26(3):150–166, 1986.Google Scholar
  5. 5.
    W. Förstner and E. Gülch. A Fast Operator for Detection and Precise Location of Distinct Points, Corners and Centres of Circular Features. In Proc. Intercommission Conference on Fast Processing on Photogrammetric Data, pages 281–305, Interlaken,Switzerland, 1987.Google Scholar
  6. 6.
    L. Kitchen and A. Rosenfeld. Gray-level corner detection. Pattern Recognition Letters, 1(2):95–102, 1982.CrossRefGoogle Scholar
  7. 7.
    T. Lindeberg. Junction Detection with Automatic Selection of Detection Scales and Localization Scales. In Proc. First International Conference on Image Processing, volume 1, pages 924–928, Austin,TX,USA, 1994.Google Scholar
  8. 8.
    J.A. Noble. Finding corners. In Proc. Third Alvey Vision Conference, pages 267–274, Cambridge,UK, 1987.Google Scholar
  9. 9.
    M. Okutomi and T. Kanade. A Locally Adaptive Window for Signal Matching. International Journal of Computer Vision, 7(2):143–162, 1992.CrossRefGoogle Scholar
  10. 10.
    K. Rohr. Untersuchung von grauwertabhängigen Transformationen zur Ermittlung des optischen Flusses in Bildfolgen. Diplomarbeit, Institut für Nachrichtentechnik, Universität Karlsruhe, 1987.Google Scholar
  11. 11.
    K.Rohr. Modelling and identification of characteristic intensity variations. Image and Vision Computing, 10(3):66–76, 1992.CrossRefGoogle Scholar
  12. 12.
    K. Rohr. Recognizing Corners by Fitting Parametric Models. International Journal of Computer Vision, 9(3):213–230, 1992.CrossRefGoogle Scholar
  13. 13.
    K. Rohr. Localization Properties of Direct Corner Detectors. Journal of Mathematical Imaging and Vision, 4(2):139–150, 1994.MathSciNetCrossRefGoogle Scholar
  14. 14.
    K. Rohr. On 3D differential operators for detecting point landmarks. Image and Vision Computing, 15(3):219–233, 1997.CrossRefGoogle Scholar
  15. 15.
    J.-P. Thirion. Extremal Points: Definition and Application to 3D Image Registration. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 587–592, Seattle,WA,USA, 1994.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Sönke Frantz
    • 1
  • Karl Rohr
    • 1
  • H. Siegfried Stiehl
    • 1
  1. 1.Fachbereich Informatik Arbeitsbereich Kognitive SystemeUniversität HamburgHamburgGermany

Personalised recommendations