Pose Invariant Deformable Shape Priors Using L1 Higher Order Sparse Graphs

  • Bo Xiang
  • Nikos Komodakis
  • Nikos Paragios
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8033)


In this paper we propose a novel method for knowledge-based segmentation. We adopt a point distribution graphical model formulation which encodes pose invariant shape priors through L 1 sparse higher order cliques. Local shape deformation properties of the model can be captured and learned in an optimal manner from a training set using dual decomposition. These higher order shape terms are combined with conventional visual ones aiming at maximizing the posterior segmentation likelihood. The considered graphical model is optimized using dual decomposition and is used towards 2D (computer vision) and 3D object segmentation (medical imaging) with promising results.


Markov Random Fields Active Shape Model Dissimilarity Function Shape Prior Dual Decomposition 
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.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. IJCV 1, 321–331 (1988)CrossRefGoogle Scholar
  2. 2.
    Cootes, T., Taylor, C., Cooper, D., Graham, J., et al.: Active shape models-their training and application. Computer Vision and Image Understanding 61, 38–59 (1995)CrossRefGoogle Scholar
  3. 3.
    Chen, Y., Tagare, H., Thiruvenkadam, S., Huang, F., Wilson, D., Gopinath, K., Briggs, R., Geiser, E.: Using prior shapes in geometric active contours in a variational framework. IJCV (2002)Google Scholar
  4. 4.
    Rousson, M., Paragios, N.: Prior knowledge, level set representations & visual grouping. IJCV (2008)Google Scholar
  5. 5.
    Cremers, D., Osher, S., Soatto, S.: Kernel density estimation and intrinsic alignment for shape priors in level set segmentation. IJCV (2006)Google Scholar
  6. 6.
    Freedman, D., Zhang, T.: Interactive graph cut based segmentation with shape priors. In: CVPR, vol. 1, pp. 755–762 (2005)Google Scholar
  7. 7.
    Grady, L.: Random Walks for Image Segmentation. PAMI 28, 1768–1783 (2006)CrossRefGoogle Scholar
  8. 8.
    Seghers, D., Hermans, J., Loeckx, D., Maes, F., Vandermeulen, D., Suetens, P.: Model-based segmentation using graph representations. In: Metaxas, D., Axel, L., Fichtinger, G., Székely, G. (eds.) MICCAI 2008, Part I. LNCS, vol. 5241, pp. 393–400. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  9. 9.
    Besbes, A., Komodakis, N., Langs, G., Paragios, N.: Shape priors and discrete mrfs for knowledge-based segmentation. In: CVPR (2009)Google Scholar
  10. 10.
    Xiang, B., Wang, C., Deux, J., Rahmouni, A., Paragios, N.: 3d cardiac segmentation with pose-invariant higher-order mrfs. In: ISBI, pp. 1425–1428 (2012)Google Scholar
  11. 11.
    Komodakis, N.: Efficient training for pairwise or higher order crfs via dual decomposition. In: CVPR, pp. 1841–1848 (2011)Google Scholar
  12. 12.
    Komodakis, N., Paragios, N., Tziritas, G.: MRF optimization via dual decomposition: Message-passing revisited. In: ICCV (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Bo Xiang
    • 1
    • 2
  • Nikos Komodakis
    • 1
    • 3
    • 4
  • Nikos Paragios
    • 1
    • 2
  1. 1.Center for Learning and Visual Computing Ecole Centrale de ParisEcole des Ponts ParisTechFrance
  2. 2.INRIA SaclayEquipe GALENÎle-de-FranceFrance
  3. 3.Ecole des Ponts ParisTechUniversité Paris-EstFrance
  4. 4.Laboratoire d’Informatique Gaspard-Monge, CNRSUMRFrance

Personalised recommendations