Advertisement

Multimodal Prior Appearance Models Based on Regional Clustering of Intensity Profiles

  • François Chung
  • Hervé Delingette
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5762)

Abstract

Model-based image segmentation requires prior information about the appearance of a structure in the image. Instead of relying on Principal Component Analysis such as in Statistical Appearance Models, we propose a method based on a regional clustering of intensity profiles that does not rely on an accurate pointwise registration. Our method is built upon the Expectation-Maximization algorithm with regularized covariance matrices and includes spatial regularization. The number of appearance regions is determined by a novel model order selection criterion. The prior is described on a reference mesh where each vertex has a probability to belong to several intensity profile classes.

Keywords

Posterior Probability Covariance Matrice Appearance Model Regional Cluster Cluster Validity Index 
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.

References

  1. 1.
    Cootes, T., Taylor, C.: Using grey-level models to improve active shape model search. In: Proceedings of ICPRE, vol. 1, pp. 63–67 (1994)Google Scholar
  2. 2.
    Gilles, B.: Anatomical and kinematical modelling of the musculoskeletal system from MRI. Phd Thesis, University of Geneva (August 2007)Google Scholar
  3. 3.
    Heimann, T.: Statistical Shape Models for 3D Medical Image Segmentation. VDM Verlag Dr. Muller Aktiengesellschaft & Co., KG (2009)Google Scholar
  4. 4.
    Schneider, T.: Analysis of incomplete climate data. J. Clim. 14(5), 853–871 (2001)CrossRefGoogle Scholar
  5. 5.
    Schwarz, G.: Estimating the dimension of a model. Ann. Stat. 6(2), 461–464 (1978)zbMATHCrossRefGoogle Scholar
  6. 6.
    Kim, D.W., Lee, K.H., Lee, D.: On cluster validity index for estimation of the optimal number of fuzzy clusters. Pattern Recognition 37, 2009–2025 (2004)CrossRefGoogle Scholar
  7. 7.
    Saha, S., Bandyopadhyay, S.: A new cluster validity index based on fuzzy granulation-degranulation criterion. In: 15th ADCOM 2007, pp. 353–358 (2007)Google Scholar
  8. 8.
    Ambroise, C., Dang, M., Govaert, G.: Clustering of spatial data by the em algorithm. Quantitative Geology and Geostatistics 9, 493–504 (1997)Google Scholar
  9. 9.
    Hathaway, R.J.: Another interpretation of the em algorithm for mixture distributions. Statistics and probability letters 4(2), 53–56 (1986)zbMATHCrossRefMathSciNetGoogle Scholar
  10. 10.
    Montagnat, J., Delingette, H.: Globally constrained deformable models for 3D object reconstruction. Signal Processing 71(2), 173–186 (1998)zbMATHCrossRefGoogle Scholar
  11. 11.
    Dang, M., Govaert, G.: Spatial fuzzy clustering using em and markov random fields. Int. Journal of System Research and Information Science, 183–202 (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • François Chung
    • 1
  • Hervé Delingette
    • 1
  1. 1.Asclepios Research TeamINRIA Sophia-AntipolisFrance

Personalised recommendations