Learning the face prior for Bayesian face recognition
Refereed conference paper presented and published in conference proceedings

Times Cited
Altmetrics Information

Other information
AbstractFor the traditional Bayesian face recognition methods, a simple prior on face representation cannot cover large variations in facial poses, illuminations, expressions, aging, and occlusions in the wild. In this paper, we propose a new approach to learn the face prior for Bayesian face recognition. First, we extend Manifold Relevance Determination to learn the identity subspace for each individual automatically. Based on the structure of the learned identity subspaces, we then propose to estimate Gaussian mixture densities in the observation space with Gaussian process regression. During the training of our approach, the leave-set-out algorithm is also developed for overfitting avoidance. On extensive experimental evaluations, the learned face prior can improve the performance of the traditional Bayesian face and other related methods significantly. It is also proved that the simple Bayesian face method with the learned face prior can handle the complex intra-personal variations such as large poses and large occlusions. Experiments on the challenging LFW benchmark shows that our algorithm outperforms most of the state-of-art methods. © 2014 Springer International Publishing.
All Author(s) ListLu C., Tang X.
Name of Conference13th European Conference on Computer Vision, ECCV 2014
Start Date of Conference06/09/2014
End Date of Conference12/09/2014
Place of ConferenceZurich
Country/Region of ConferenceSwitzerland
Volume Number8692 LNCS
Issue NumberPART 4
PublisherSpringer Verlag
Place of PublicationGermany
Pages119 - 134
LanguagesEnglish-United Kingdom

Last updated on 2020-19-10 at 01:52