On compositional Image Alignment, with an application to Active Appearance Models

Efficient and accurate fitting of active appearance models (AAM) is a key requirement for many applications. The most efficient fitting algorithm today is inverse compositional image alignment (ICIA). While ICIA is extremely fast, it is also known to have a small convergence radius. Convergence is especially bad when training and testing images differ strongly, as in multi-person AAMs. We describe “forward” compositional image alignment in a consistent framework which also incorporates methods previously termed “inverse” compositional, and use it to develop two novel fitting methods. The first method, compositional gradient descent (CoDe), is approximately four times slower than ICIA, while having a convergence radius which is even larger than that achievable by direct quasi-Newton descent. An intermediate convergence range with the same speed as ICIA is achieved by LinCoDe, the second new method. The success rate of the novel methods is 10 to 20 times higher than that of the original ICIA method.

[1]  Jiri Matas,et al.  XM2VTSDB: The Extended M2VTS Database , 1999 .

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

[3]  Bernd Radig,et al.  Learning Local Objective Functions for Robust Face Model Fitting , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

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

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

[7]  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.

[8]  Sartaj Sahni,et al.  An efficient motion estimator with application to medical image registration , 1998, Medical Image Anal..

[9]  Mikkel B. Stegmann,et al.  The IMM Face Database, An Annotated Dataset of 240 Face Images , 2004 .

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

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

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

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