File(s) under permanent embargo
Learning Boltzmann distance metric for face recognition
conference contribution
posted on 2012-01-01, 00:00 authored by Truyen TranTruyen Tran, Quoc-Dinh Phung, Svetha VenkateshSvetha VenkateshWe introduce a new method for face recognition using a versatile probabilistic model known as Restricted Boltzmann Machine (RBM). In particular, we propose to regularise the standard data likelihood learning with an information-theoretic distance metric defined on intra-personal images. This results in an effective face representation which captures the regularities in the face space and minimises the intra-personal variations. In addition, our method allows easy incorporation of multiple feature sets with controllable level of sparsity. Our experiments on a high variation dataset show that the proposed method is competitive against other metric learning rivals. We also investigated the RBM method under a variety of settings, including fusing facial parts and utilising localised feature detectors under varying resolutions. In particular, the accuracy is boosted from 71.8% with the standard whole-face pixels to 99.2% with combination of facial parts, localised feature extractors and appropriate resolutions.
History
Event
IEEE Multimedia and Expo Conference (13th : 2012 : Melbourne, Victoria)Pagination
218 - 223Publisher
IEEELocation
Melbourne, VictoriaPlace of publication
Piscataway, N.J.Publisher DOI
Start date
2012-07-09End date
2012-07-13ISBN-13
9780769547114Language
engPublication classification
E1 Full written paper - refereedCopyright notice
2012, IEEETitle of proceedings
ICME 2012 : Proceedings of the 13th IEEE International Conference on Multimedia and ExpoUsage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC