Metric Learning for Image Alignment

Image alignment has been a long standing problem in computer vision. Parameterized Appearance Models (PAMs) such as the Lucas-Kanade method, Eigentracking, and Active Appearance Models are commonly used to align images with respect to a template or to a previously learned model. While PAMs have numerous advantages relative to alternate approaches, they have at least two drawbacks. First, they are especially prone to local minima in the registration process. Second, often few, if any, of the local minima of the cost function correspond to acceptable solutions. To overcome these problems, this paper proposes a method to learn a metric for PAMs that explicitly optimizes that local minima occur at and only at the places corresponding to the correct fitting parameters. To the best of our knowledge, this is the first paper to address the problem of learning a metric to explicitly model local properties of the PAMs’ error surface. Synthetic and real examples show improvement in alignment performance in comparison with traditional approaches. In addition, we show how the proposed criteria for a good metric can be used to select good features to track.

[1]  Timothy F. Cootes,et al.  Statistical models of appearance for computer vision , 1999 .

[2]  Erik G. Learned-Miller,et al.  Data driven image models through continuous joint alignment , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  C Tomasi,et al.  Shape and motion from image streams: a factorization method. , 1992, Proceedings of the National Academy of Sciences of the United States of America.

[4]  Stephan Tschechne,et al.  Learning Robust Objective Functions for Model Fitting in Image Understanding Applications , 2006, BMVC.

[5]  Thomas Hofmann,et al.  Large Margin Methods for Structured and Interdependent Output Variables , 2005, J. Mach. Learn. Res..

[6]  Minh Hoai Learning Image Alignment without Local Minima for Face Detection and Tracking , 2008 .

[7]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Kenichi Kanatani,et al.  Statistical optimization for geometric computation - theory and practice , 1996, Machine intelligence and pattern recognition.

[9]  Stephen P. Boyd,et al.  Graph Implementations for Nonsmooth Convex Programs , 2008, Recent Advances in Learning and Control.

[10]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[11]  Jordi Vitrià,et al.  Eigenfiltering for flexible eigentracking (EFE) , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[12]  P. Anandan,et al.  Hierarchical Model-Based Motion Estimation , 1992, ECCV.

[13]  Ben Taskar,et al.  Max-Margin Markov Networks , 2003, NIPS.

[14]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[15]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Takahiro Ishikawa,et al.  The template update problem , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Takeo Kanade,et al.  Real-time combined 2D+3D active appearance models , 2004, CVPR 2004.

[18]  G Learned-MillerErik Data Driven Image Models through Continuous Joint Alignment , 2006 .

[19]  Thomas Vetter,et al.  Learning novel views to a single face image , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[20]  Michael J. Black,et al.  Eigentracking: Robust matching and tracking of objects using view - based representation , 1998 .

[21]  Rong Jin,et al.  Distance Metric Learning: A Comprehensive Survey , 2006 .

[22]  Simon Baker,et al.  Lucas-Kanade 20 Years On: A Unifying Framework , 2004, International Journal of Computer Vision.

[23]  W. Rudin Real and complex analysis, 3rd ed. , 1987 .

[24]  Xiaoming Liu,et al.  Generic Face Alignment using Boosted Appearance Model , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Roland Göcke,et al.  A Nonlinear Discriminative Approach to AAM Fitting , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[26]  Fernando De la Torre,et al.  Parameterized Kernel Principal Component Analysis: Theory and applications to supervised and unsupervised image alignment , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  Thomas Vetter,et al.  A morphable model for the synthesis of 3D faces , 1999, SIGGRAPH.

[28]  Hao Wu,et al.  Face alignment via boosted ranking model , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Simon Baker,et al.  Equivalence and efficiency of image alignment algorithms , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[30]  Timothy F. Cootes,et al.  Statistical models of appearance for medical image analysis and computer vision , 2001, SPIE Medical Imaging.

[31]  Simon Baker,et al.  Active Appearance Models Revisited , 2004, International Journal of Computer Vision.

[32]  W. Rudin Principles of mathematical analysis , 1964 .

[33]  Michael J. Black,et al.  EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation , 1996, International Journal of Computer Vision.

[34]  Gregory D. Hager,et al.  Efficient Region Tracking With Parametric Models of Geometry and Illumination , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[35]  Shaogang Gong,et al.  Dynamic Vision - From Images to Face Recognition , 2000 .

[36]  Peter Meer,et al.  Estimation of Nonlinear Errors-in-Variables Models for Computer Vision Applications , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Ian T. Jolliffe,et al.  Principal Component Analysis , 2002, International Encyclopedia of Statistical Science.

[38]  Minh Hoai Local Minima Free Parameterized Appearance Models , 2008 .

[39]  Tomaso A. Poggio,et al.  Multidimensional morphable models , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[40]  S. Nayar,et al.  Early Visual Learning , 1996 .

[41]  Takeo Kanade,et al.  Filtered Component Analysis to Increase Robustness to Local Minima in Appearance Models , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[42]  Michael J. Black,et al.  Robust parameterized component analysis: theory and applications to 2D facial appearance models , 2003, Comput. Vis. Image Underst..