Show simple item record

dc.contributor.authorTran, Truyen
dc.contributor.authorPhung, D.
dc.contributor.authorVenkatesh, S.
dc.contributor.editorNot known
dc.identifier.citationTran, Truyen and Phung, Dinh Q. and Venkatesh, Svetha. 2012. Learning Boltzmann distance metric for face recognition, in IEEE International Conference on Multimedia and Expo (ICME), Jul 9-13 2012, pp. 218-223. Melbourne: IEEE.

We 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 utilizing 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.

dc.titleLearning Boltzmann distance metric for face recognition
dc.typeConference Paper
dcterms.source.titleIEEE Int. Conf. on Multimedia & Expo
dcterms.source.seriesIEEE Int. Conf. on Multimedia & Expo
dcterms.source.conferenceICME 2012
dcterms.source.conference-start-dateJul 9 2012
dcterms.source.placeNot known
curtin.accessStatusOpen access

Files in this item


This item appears in the following Collection(s)

Show simple item record