Learning Deformations with Parallel Transport

  • Donglai Wei
  • Dahua Lin
  • John FisherIII
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7573)


Many vision problems, such as object recognition and image synthesis, are greatly impacted by deformation of objects. In this paper, we develop a deformation model based on Lie algebraic analysis. This work aims to provide a generative model that explicitly decouples deformation from appearance, which is fundamentally different from the prior work that focuses on deformation-resilient features or metrics. Specifically, the deformation group for each object can be characterized by a set of Lie algebraic basis. Such basis for different objects are related via parallel transport. Exploiting the parallel transport relations, we formulate an optimization problem, and derive an algorithm that jointly estimates the deformation basis for a class of objects, given a set of images resulted from the action of the deformations. We test the proposed model empirically on both character recognition and face synthesis.


Tangent Space Parallel Transport Deformation Model Active Appearance Model Standard Cluster 
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.
    Tenenbaum, J., Silva, V., Langford, J.: A global geometric framework for nonlinear dimensionality reduction. Science 290, 2319 (2000)CrossRefGoogle Scholar
  2. 2.
    Roweis, S., Saul, L.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323 (2000)CrossRefGoogle Scholar
  3. 3.
    Belongie, S., Malik, J., Puzicha, J.: Shape context: A new descriptor for shape matching and object recognition. In: Advances in Neural Information Processing Systems, pp. 831–837 (2001)Google Scholar
  4. 4.
    Keysers, D., Deselaers, T., Gollan, C., Ney, H.: Deformation models for image recognition. IEEE Trans. on Pattern Analysis and Machine Intelligence 29, 1422–1435 (2007)CrossRefGoogle Scholar
  5. 5.
    Simard, P., Cun, Y.L., Denker, J., Victorri, B.: Transformation invariance in pattern recognition: Tangent distance and tangent propagation. International Journal of Imaging Systems and Technology 11, 181–197 (2000)CrossRefGoogle Scholar
  6. 6.
    Hastie, T., Simard, P.: Metrics and models for handwritten character recognition. Statistical Science, 54–65 (1998)Google Scholar
  7. 7.
    Keysers, D., Macherey, W., Ney, H., Dahmen, J.: Adaptation in statistical pattern recognition using tangent vectors. IEEE Transactions on Pattern Analysis and Machine Intelligence 26, 269–274 (2004)CrossRefGoogle Scholar
  8. 8.
    Frey, B., Jojic, N.: Transformed component analysis: Joint estimation of spatial transformations and image components. In: The Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 2, pp. 1190–1196. IEEE (1999)Google Scholar
  9. 9.
    Frey, B., Jojic, N.: Estimating mixture models of images and inferring spatial transformations using the em algorithm. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1. IEEE (1999)Google Scholar
  10. 10.
    Frey, B., Jojic, N.: Transformation-invariant clustering using the em algorithm. IEEE Transactions on Pattern Analysis and Machine Intelligence 25, 1–17 (2003)CrossRefGoogle Scholar
  11. 11.
    Miller, E., Matsakis, N., Viola, P.: Learning from one example through shared densities on transforms. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 464–471. IEEE (2000)Google Scholar
  12. 12.
    Cootes, T., Edwards, G., Taylor, C.: Active appearance models. IEEE Transactions on Pattern Analysis and Machine Intelligence 23, 681–685 (2001)CrossRefGoogle Scholar
  13. 13.
    Jones, M., Poggio, T.: Multidimensional morphable models: A framework for representing and matching object classes. International Journal of Computer Vision 29, 107–131 (1998)CrossRefGoogle Scholar
  14. 14.
    Bruhn, A., Weickert, J., Schnörr, C.: Lucas/kanade meets horn/schunck: Combining local and global optic flow methods. International Journal of Computer Vision 61, 211–231 (2005)CrossRefGoogle Scholar
  15. 15.
    LeCun, Y.: Mnist handwritten digit database. AT&T Labs (Online) (1998),

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Donglai Wei
    • 1
  • Dahua Lin
    • 1
  • John FisherIII
    • 1

Personalised recommendations