Probabilistic constrained adaptive local displacement experts

Generic non-rigid face fitting, namely the task of finding the configuration of a shape model describing a face in an image under variations in identity, illumination, pose and expression, is addressed in this work through an ensemble of local patch-based displacement experts. To account for appearance variations, these displacement experts are parameterized bilinearly, allowing the experts to adapt to the face at hand. The problem is formulated probabilistically, where the objective is to maximize the likelihood of predicted displacements marginalized over the adaptation parameters. The efficacy of the proposed formulation is compared empirically against a two existing methods.

[1]  Sami Romdhani,et al.  Efficient, robust and accurate fitting of a 3D morphable model , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[2]  Jason M. Saragih,et al.  Non-rigid Face Tracking with Local Appearance Consistency Constraint. , 2008, Image and vision computing.

[3]  Andrew W. Fitzgibbon,et al.  Damped Newton algorithms for matrix factorization with missing data , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

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

[5]  Michael E. Tipping,et al.  Probabilistic Principal Component Analysis , 1999 .

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

[7]  C. Taylor,et al.  Active shape models - 'Smart Snakes'. , 1992 .

[8]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[9]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

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

[11]  Fernando De la Torre,et al.  Bilinear Active Appearance Models , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[12]  K. Walker,et al.  View-based active appearance models , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[13]  Aaron Hertzmann,et al.  Nonrigid Structure-from-Motion: Estimating Shape and Motion with Hierarchical Priors , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Joshua B. Tenenbaum,et al.  Separating Style and Content with Bilinear Models , 2000, Neural Computation.

[15]  Dorin Comaniciu,et al.  Shape Regression Machine , 2007, IPMI.

[16]  Ralph Gross,et al.  Generic vs. person specific active appearance models , 2005, Image Vis. Comput..

[17]  Simon Lucey,et al.  Deformable Face Fitting with Soft Correspondence Constraints , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[18]  Yang Wang,et al.  Enforcing convexity for improved alignment with constrained local models , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Timothy F. Cootes,et al.  Feature Detection and Tracking with Constrained Local Models , 2006, BMVC.

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

[21]  Timothy F. Cootes,et al.  Boosted Regression Active Shape Models , 2007, BMVC.

[22]  Timothy F. Cootes,et al.  A comparison of shape constrained facial feature detectors , 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..

[23]  Adrien Bartoli,et al.  Segmented AAMs Improve Person-Independent Face Fitting , 2007 .

[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.  Iterative Error Bound Minimisation for AAM Alignment , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

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

[27]  Ralph Gross,et al.  Semi-supervised learning of multi-factor models for face de-identification , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.