Face alignment through subspace constrained mean-shifts
- 1 September 2009
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1034-1041
- https://doi.org/10.1109/iccv.2009.5459377
Abstract
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. This simplification substitutes the true objective with a smoothed version of itself, reducing sensitivity to local minima and outlying detections. In this work, a principled optimization strategy is proposed where a nonparametric representation of the landmark distributions is maximized within a hierarchy of smoothed estimates. The resulting update equations are reminiscent of mean-shift but with a subspace constraint placed on the shape's variability. This approach is shown to outperform other existing methods on the task of generic face fitting.Keywords
This publication has 8 references indexed in Scilit:
- Enforcing convexity for improved alignment with constrained local modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Generic Face Alignment using Boosted Appearance ModelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- A Nonlinear Discriminative Approach to AAM FittingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Mean shift is a bound optimizationIeee Transactions On Pattern Analysis and Machine Intelligence, 2005
- Active Appearance Models RevisitedInternational Journal of Computer Vision, 2004
- A comparison of shape constrained facial feature detectorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Mean shift, mode seeking, and clusteringIeee Transactions On Pattern Analysis and Machine Intelligence, 1995
- Active Shape Models — ‘Smart Snakes’Published by Springer Science and Business Media LLC ,1992