Learning Deformations with Parallel Transport

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.

[1]  Brendan J. Frey,et al.  Estimating mixture models of images and inferring spatial transformations using the EM algorithm , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[2]  Patrice Y. Simard,et al.  Metrics and Models for Handwritten Character Recognition , 1998 .

[3]  Bernard Victorri,et al.  Transformation invariance in pattern recognition: Tangent distance and propagation , 2000 .

[4]  Joachim Weickert,et al.  Lucas/Kanade Meets Horn/Schunck: Combining Local and Global Optic Flow Methods , 2005, International Journal of Computer Vision.

[5]  Jitendra Malik,et al.  Shape Context: A New Descriptor for Shape Matching and Object Recognition , 2000, NIPS.

[6]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[7]  Yann LeCun,et al.  Transformation Invariance in Pattern Recognition-Tangent Distance and Tangent Propagation , 1996, Neural Networks: Tricks of the Trade.

[8]  Brendan J. Frey,et al.  Transformed component analysis: joint estimation of spatial transformations and image components , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[9]  Michael Jones,et al.  Multidimensional Morphable Models: A Framework for Representing and Matching Object Classes , 2004, International Journal of Computer Vision.

[10]  JojicNebojsa,et al.  Transformation-Invariant Clustering Using the EM Algorithm , 2003 .

[11]  Paul A. Viola,et al.  Learning from one example through shared densities on transforms , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[12]  Hermann Ney,et al.  Adaptation in statistical pattern recognition using tangent vectors , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

[14]  B. Frey,et al.  Transformation-Invariant Clustering Using the EM Algorithm , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Hermann Ney,et al.  Deformation Models for Image Recognition , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.