International Journal of Computer Vision

, Volume 91, Issue 2, pp 200–215

Deformable Model Fitting by Regularized Landmark Mean-Shift



Deformable model fitting has been actively pursued in the computer vision community for over a decade. As a result, numerous approaches have been proposed with varying degrees of success. A class of approaches that has shown substantial promise is one that makes independent predictions regarding locations of the model’s landmarks, which are combined by enforcing a prior over their joint motion. A common theme in innovations to this approach is the replacement of the distribution of probable landmark locations, obtained from each local detector, with simpler parametric forms. In this work, a principled optimization strategy is proposed where nonparametric representations of these likelihoods are maximized within a hierarchy of smoothed estimates. The resulting update equations are reminiscent of mean-shift over the landmarks but with regularization imposed through a global prior over their joint motion. Extensions to handle partial occlusions and reduce computational complexity are also presented. Through numerical experiments, this approach is shown to outperform some common existing methods on the task of generic face fitting.


Deformable Registration Mean-shift 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  • Jason M. Saragih
    • 1
  • Simon Lucey
    • 2
  • Jeffrey F. Cohn
    • 3
  1. 1.ICT Center, CSIROSydneyAustralia
  2. 2.ICT Center, CSIROBrisbaneAustralia
  3. 3.Robotics InstituteCarnegie Mellon UniversityPittsburghUSA

Personalised recommendations