Face alignment using boosted ranking models

Wu, H., Liu, X., and Doretto, G.
Face alignment using boosted ranking models
In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1–8, 2008.
Oral Presentation

Download

PDF (1017.4kB )  

Abstract

Face alignment seeks to deform a face model to match it with the features of the image of a face by optimizing an appropriate cost function. We propose a new face model that is aligned by maximizing a score function, which we learn from training data, and that we impose to be concave. We show that this problem can be reduced to learning a classifier that is able to say whether or not by switching from one alignment to a new one, the model is approaching the correct fitting. This relates to the ranking problem where a number of instances need to be ordered. For training the model, we propose to extend GentleBoost [23] to ranklearning. Extensive experimentation shows the superiority of this approach to other learning paradigms, and demonstrates that this model exceeds the alignment performance of the state-of-the-art.

@INPROCEEDINGS{wuLD08cvpr,
  author = {Wu, H. and Liu, X. and Doretto, G.},
  title = {Face alignment using boosted ranking models},
  booktitle = cvpr,
  year = {2008},
  pages = {1--8},
  note = {\btohremove{\textsf{\textbf{AR: XX.X\%}}}},
  bib2html_pubtype = {Refereed Conferences},
  bib2html_rescat = {Video Surveillance, Appearance Modeling, Shape and Appearance Modeling,
	Integral Image Computations, Face Tracking, Face Modeling},
  abstract = {Face alignment seeks to deform a face model to match it with the features
	of the image of a face by optimizing an appropriate cost function.
	We propose a new face model that is aligned by maximizing a score
	function, which we learn from training data, and that we impose to
	be concave. We show that this problem can be reduced to learning
	a classifier that is able to say whether or not by switching from
	one alignment to a new one, the model is approaching the correct
	fitting. This relates to the ranking problem where a number of instances
	need to be ordered. For training the model, we propose to extend
	GentleBoost [23] to ranklearning. Extensive experimentation shows
	the superiority of this approach to other learning paradigms, and
	demonstrates that this model exceeds the alignment performance of
	the state-of-the-art.},
  file = {wuLD08cvpr.pdf:doretto\\conference\\wuLD08cvpr.pdf:PDF},
  owner = {doretto},
  pdf = {doretto\conference\wuLD08cvpr.pdf},
  timestamp = {2008.01.16},
  wwwnote = {<span class="wwwnote">Oral Presentation</span>}
}

Generated by bib2html.pl (written by Patrick Riley )