Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/TPAMI.2013.23 | Pattern Analysis and Machine Intelligence, IEEE Transactions |
Keywords | Field | DocType |
objective function,pose,detectors,expression,optimization,feature extraction,face recognition,hidden variables,lighting | Facial recognition system,Computer vision,Biometrics access control,Pattern recognition,Computer science,Feature extraction,Nonparametric statistics,Artificial intelligence,Hidden variable theory,Biometrics,Shape analysis (digital geometry),Bayesian probability | Conference |
Volume | Issue | ISSN |
35 | 12 | 0162-8828 |
ISBN | Citations | PageRank |
978-1-4577-0394-2 | 227 | 7.38 |
References | Authors | |
22 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Peter N. Belhumeur | 1 | 12242 | 1001.27 |
David W. Jacobs | 2 | 4599 | 348.03 |
D. J. Kriegman | 3 | 653 | 108.98 |
Neeraj Kumar | 4 | 1623 | 74.67 |