Advertisement

Patch-Based Low-Rank Matrix Completion for Learning of Shape and Motion Models from Few Training Samples

  • Jan EhrhardtEmail author
  • Matthias Wilms
  • Heinz Handels
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9908)

Abstract

Statistical models have opened up new possibilities for the automated analysis of images. However, the limited availability of representative training data, e.g. segmented images, leads to a bottleneck for the application of statistical models in practice. In this paper, we propose a novel patch-based technique that enables to learn representative statistical models of shape, appearance, or motion with a high grade of detail from a small number of observed training samples using low-rank matrix completion methods. Our method relies on the assumption that local variations have limited effects in distant areas. We evaluate our approach on three exemplary applications: (1) 2D shape modeling of faces, (2) 3D modeling of human lung shapes, and (3) population-based modeling of respiratory organ deformation. A comparison with the classical PCA-based modeling approach and FEM-PCA shows an improved generalization ability for small training sets indicating the improved flexibility of the model.

Keywords

Statistical modeling High-dimension-low-sample-size problem Low-rank matrix completion Virtual samples 

Notes

Acknowledgement

This work was supported by the German Research Foundation (DFG EH 224/6-1).

References

  1. 1.
    Armato, S.G., et al.: The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans. Med. Phys. 38(2), 915–931 (2011)CrossRefGoogle Scholar
  2. 2.
    Balzano, L., Wright, S.J.: On GROUSE and incremental SVD. In: Computational Advances in Multi-sensor Adaptive Processing (CAMSAP), pp. 1–4 (2013)Google Scholar
  3. 3.
    Cai, J.F., Candès, E.J., Shen, Z.: A singular value thresholding algorithm for matrix completion. SIAM J. Optim. 20(4), 1956–1982 (2010)MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    Candès, E.J., Recht, B.: Exact matrix completion via convex optimization. Found. Comput. Math. 9(6), 717–772 (2009)MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Cerrolaza, J.J., Reyes, M., Summers, R.M., Ballester, M.A.G., Linguraru, M.G.: Automatic multi-resolution shape modeling of multi-organ structures. Med. Image Anal. 25(1), 11–21 (2015)CrossRefGoogle Scholar
  6. 6.
    Cootes, T.F., Taylor, C.J.: Combining point distribution models with shape models based on finite element analysis. Image Vis. Comput. 13(5), 403–409 (1995)CrossRefGoogle Scholar
  7. 7.
    Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active shape models-their training and application. Comput. Vis. Image Underst. 61(1), 38–59 (1995)CrossRefGoogle Scholar
  8. 8.
    Davatzikos, C., Tao, X., Shen, D.: Hierarchical active shape models, using the wavelet transform. IEEE Trans. Med. Imaging 22(3), 414–423 (2003)CrossRefGoogle Scholar
  9. 9.
    Davies, R.H., Twining, C.J., Cootes, T.F., Waterton, J.C., Taylor, C.J.: A minimum description length approach to statistical shape modeling. IEEE Trans. Med. Imaging 21(5), 525–537 (2002)CrossRefzbMATHGoogle Scholar
  10. 10.
    Ehrhardt, J., Werner, R., Schmidt-Richberg, A., Handels, H.: Statistical modeling of 4D respiratory lung motion using diffeomorphic image registration. IEEE Trans. Med. Imaging 30(2), 251–265 (2011)CrossRefGoogle Scholar
  11. 11.
    Friedel, I., Schröder, P., Desbrun, M.: Unconstrained spherical parameterization. J. Graph. GPU Game Tools 12(1), 17–26 (2007)CrossRefGoogle Scholar
  12. 12.
    He, J., Balzano, L., Szlam, A.: Incremental gradient on the grassmannian for online foreground and background separation in subsampled video. CVPR 2012, 1568–1575 (2012)Google Scholar
  13. 13.
    Heimann, T., Meinzer, H.P.: Statistical shape models for 3D medical image segmentation: a review. Med. Image Anal. 13(4), 543–563 (2009)CrossRefGoogle Scholar
  14. 14.
    Kennedy, R., Taylor, C.J., Balzano, L.: Online completion of ill-conditioned low-rank matrices. In: IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp. 507–511 (2014)Google Scholar
  15. 15.
    Koikkalainen, J., Tolli, T., Lauerma, K., Antila, K., Mattila, E., Lilja, M., Lotjonen, J.: Methods of artificial enlargement of the training set for statistical shape models. IEEE Trans. Med. Imaging 27(11), 1643–1654 (2008)CrossRefGoogle Scholar
  16. 16.
    Kumar, R., Banerjee, A., Vemuri, B.C., Pfister, H.: Maximizing all margins: pushing face recognition with kernel plurality. ICCV 2011, 2375–2382 (2011)Google Scholar
  17. 17.
    Lai, R.Y., Yuen, P.C.: ProPPA: a fast algorithm for \(\ell _1\) minimization and low-rank matrix completion, May 2012. arXiv preprint arXiv:1205.0088
  18. 18.
    Leopardi, P.: A partition of the unit sphere into regions of equal area and small diameter. Electr. Trans. Numer. Anal. 25(12), 309–327 (2006)MathSciNetzbMATHGoogle Scholar
  19. 19.
    Lu, J., Tan, Y.P., Wang, G.: Discriminative multi-manifold analysis for face recognition from a single training sample per person. ICCV 2011, 1943–1950 (2011)Google Scholar
  20. 20.
    Lüthi, M., Albrecht, T., Vetter, T.: Building shape models from lousy data. In: Yang, G.-Z., Hawkes, D., Rueckert, D., Noble, A., Taylor, C. (eds.) MICCAI 2009, Part II. LNCS, vol. 5762, pp. 1–8. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  21. 21.
    Mishra, B.: A Riemannian approach to large-scale constrained least-squares with symmetries. Ph.D. thesis, Université de Namur (2014)Google Scholar
  22. 22.
    Ngo, T., Saad, Y.: Scaled gradients on grassmann manifolds for matrix completion. NIPS 2012, 1412–1420 (2012)Google Scholar
  23. 23.
    Nordstrøm, M.M., Larsen, M., Sierakowski, J., Stegmann, M.B.: The IMM face database-an annotated dataset of 240 face images. Technical report, Technical University of Denmark, DTU Informatics (2004)Google Scholar
  24. 24.
    Onofrey, J., Papademetris, X., Staib, L.: Low-dimensional non-rigid image registration using statistical deformation models from semi-supervised training data. IEEE Trans. Med. Imaging 34(7), 1522–1532 (2015)CrossRefGoogle Scholar
  25. 25.
    Rueckert, D., Frangi, A.F., Schnabel, J.A.: Automatic construction of 3D statistical deformation models using non-rigid registration. In: Niessen, W.J., Viergever, M.A. (eds.) MICCAI 2001. LNCS, vol. 2208, pp. 77–84. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  26. 26.
    Shamir, A.: A survey on mesh segmentation techniques. Comput. Graph. Forum 27(6), 1539–1556 (2008)CrossRefzbMATHGoogle Scholar
  27. 27.
    Turk, M.A., Pentland, A.P.: Face recognition using eigenfaces. In: CVPR 1991, pp. 586–591. IEEE (1991)Google Scholar
  28. 28.
    Werner, R., Schmidt-Richberg, A., Handels, H., Ehrhardt, J.: Estimation of lung motion fields in 4D CT data by variational non-linear intensity-based registration: a comparison and evaluation study. Phys. Med. Biol. 59, 4247–4260 (2014)CrossRefGoogle Scholar
  29. 29.
    Zhang, D., Chen, S., Zhou, Z.H.: A new face recognition method based on SVD perturbation for single example image per person. Appl. Math. Comput. 163(2), 895–907 (2005)MathSciNetCrossRefzbMATHGoogle Scholar
  30. 30.
    Zhao, Z., Aylward, S.R., Teoh, E.-K.: A novel 3D partitioned active shape model for segmentation of brain MR images. In: Duncan, J.S., Gerig, G. (eds.) MICCAI 2005. LNCS, vol. 3749, pp. 221–228. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  31. 31.
    Zhu, P., Zhang, L., Hu, Q., Shiu, S.C.K.: Multi-scale patch based collaborative representation for face recognition with margin distribution optimization. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part I. LNCS, vol. 7572, pp. 822–835. Springer, Heidelberg (2012)Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  1. 1.Institute of Medical InformaticsUniversity of LübeckLübeckGermany

Personalised recommendations