Improving the Robustness in Extracting 3D Point Landmarks Based on Deformable Models (original) (raw)

Abstract

Existing approaches to extracting 3D point landmarks based on deformable models require a good model initialization to avoid local suboptima during model fitting. To overcome this drawback, we propose a generally applicable novel hybrid optimization algorithm combining the advantages of both conjugate gradient (cg-)optimization (known for its time efficiency) and genetic algorithms (exhibiting robustness against local suboptima). We apply our algorithm to 3DMR and CTimages depicting tip-like and saddle-like anatomical structures such as the horns of the lateral ventricles in the human brain or the zygomatic bones as part of the skull. Experimental results demonstrate that the robustness of model fitting is significantly improved using hybrid optimization compared to a purely local cg-method. Moreover, we compare an edge strength- to an edge distance-based fitting measure.

Preview

Unable to display preview. Download preview PDF.

We’re sorry, something doesn't seem to be working properly.

Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

References

  1. E. Bardinet, L.D. Cohen, and N. Ayache. Superquadrics and Free-Form Deformations: A Global Model to Fit and Track 3D Medical Data. Proc.CVRMe d’95, LNCS 905, pp. 319–326. Springer, 1995.
    Google Scholar
  2. R. Bertolini and G. Leutert. Atlas der Anatomie des Menschen. Band 3: Kopf, Hals, Gehirn, Rückenmark und Sinnesorgane. Springer, 1982.
    Google Scholar
  3. J.F. Canny. A Computational Approach to Edge Detection. PAMI, 8(6):679–698, 1986.
    Google Scholar
  4. K. Delibasis and P.E. Undrill. Anatomical object recognition using deformable geometric models. Image and Vision Computing, 12(7):423–433, 1994.
    Article Google Scholar
  5. S. Frantz, K. Rohr, and H.S. Stiehl. Localization of 3D Anatomical Point Landmarks in 3D Tomographic Images Using Deformable Models. Proc. Int. Conf. on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2000), LNCS 1935, pp. 492–501, Springer, 2000.
    Google Scholar
  6. G.H. Golub and C.F. Van Loan. Matrix Computations. Johns Hopkins University Press, 1996.
    Google Scholar
  7. D. Goldberg. Genetic Algorithms in Search, Optimization and Machine Learning. Addison Wesley, 1989.
    Google Scholar
  8. S.H. Lai and B.C. Vemuri. Efficient hybrid-search for visual reconstruction problems. Image and Vision Computing, 17(1):37–49, 1999.
    Article Google Scholar
  9. T. McInerney and D. Terzopoulos. Deformable Models in Medical Image Analysis: A Survey. Medical Image Analysis, 1(2):91–108, 1996.
    Article Google Scholar
  10. D.W. Paglieroni. A Unified Distance Transform Algorithm and Architecture. Machine Vision and Applications, 5(1):47–55, 1992.
    Article Google Scholar
  11. K. Rohr. On 3D differential operators for detecting point landmarks. Image and Vision Computing, 15(3):219–233, 1997.
    Article Google Scholar
  12. J. Sobotta. Atlas der Anatomie des Menschen. Band 1: Kopf, Hals, obere Extremität, Haut. Urban & Schwarzenberg, 19th edition, 1988.
    Google Scholar
  13. F. Solina and R. Bajcsy. Recovery of Parametric Models from Range Images: the Case for Superquadrics with Global Deformations. PAMI, 12(2):131–147, 1990.
    Google Scholar
  14. L.H. Staib and J.S. Duncan. Model-Based Deformable Surface Finding for Medical Images. IEEE Trans.Me d.Imag., 15(5):720–731, 1996.
    Article Google Scholar
  15. D. Terzopoulos and D. Metaxas. Dynamic 3D Models with Local and Global Deformations: Deformable Superquadrics. PAMI, 13(7):703–714, 1991.
    Google Scholar
  16. J.-P. Thirion. New Feature Points based on Geometric Invariants for 3D Image Registration. Internat. Journal of Computer Vision, 18(2):121–137, 1996.
    Article Google Scholar
  17. V. Vaerman, G. Menegaz, and J.-P. Thiran. A Parametric Hybrid Model used for Multidimensional Object Representation. Proc.ICIP’99, vol. 1, pp. 163–167, 1999.
    Google Scholar
  18. B.C. Vemuri and A. Radisavljevic. Multiresolution Stochastic Hybrid Shape Models with Fractal Priors. ACM Trans.on Graphics, 13(2):177–207, 1994.
    Article MATH Google Scholar
  19. Z. Zhang. Parameter Estimation Techniques: A Tutorial with Application to Conic Fitting. INRIA Rapport de recherche, No. 2676, 1995.
    Google Scholar

Download references

Author information

Authors and Affiliations

  1. FB Informatik, AB Kognitive Systeme, Universität Hamburg, Vogt-Kölln-Str. 30, D-22527, Hamburg
    Manfred Alker, Sönke Frantz & H. Siegfried Stiehl
  2. International University in Germany, D-76646, Bruchsal
    Karl Rohr

Authors

  1. Manfred Alker
  2. Sönke Frantz
  3. Karl Rohr
  4. H. Siegfried Stiehl

Editor information

Editors and Affiliations

  1. Chair of Image Understanding and Knowledge Based Systems, Technical University Munich, Orleansstr. 34, 81667, Munich, Germany
    Bernd Radig & Stefan Florczyk &

Rights and permissions

© 2001 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Alker, M., Frantz, S., Rohr, K., Stiehl, H.S. (2001). Improving the Robustness in Extracting 3D Point Landmarks Based on Deformable Models. In: Radig, B., Florczyk, S. (eds) Pattern Recognition. DAGM 2001. Lecture Notes in Computer Science, vol 2191. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45404-7\_15

Download citation

Keywords

Publish with us