Localizing parts of faces using a consensus of exemplars

TitleLocalizing parts of faces using a consensus of exemplars
Publication TypeConference Papers
Year of Publication2011
AuthorsBelhumeur PN, Jacobs DW, Kriegman DJ, Kumar N
Conference NameComputer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on
Date Published2011/06//
KeywordsBayesian, faces;lighting;occlusion;pose;Bayes, function;exemplar, images;expression;face, localization;human, methods;face, objective, part, recognition;

We present a novel approach to localizing parts in images of human faces. The approach combines the output of local detectors with a non-parametric set of global models for the part locations based on over one thousand hand-labeled exemplar images. By assuming that the global models generate the part locations as hidden variables, we derive a Bayesian objective function. This function is optimized using a consensus of models for these hidden variables. The resulting localizer handles a much wider range of expression, pose, lighting and occlusion than prior ones. We show excellent performance on a new dataset gathered from the internet and show that our localizer achieves state-of-the-art performance on the less challenging BioID dataset.