Learning Boltzmann distance metric for face recognition
dc.contributor.author | Tran, Truyen | |
dc.contributor.author | Phung, D. | |
dc.contributor.author | Venkatesh, S. | |
dc.contributor.editor | Not known | |
dc.date.accessioned | 2017-01-30T10:39:43Z | |
dc.date.available | 2017-01-30T10:39:43Z | |
dc.date.created | 2013-03-27T20:01:00Z | |
dc.date.issued | 2012 | |
dc.identifier.citation | Tran, 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. | |
dc.identifier.uri | http://hdl.handle.net/20.500.11937/4527 | |
dc.identifier.doi | 10.1109/ICME.2012.131 | |
dc.description.abstract |
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.publisher | IEEE | |
dc.title | Learning Boltzmann distance metric for face recognition | |
dc.type | Conference Paper | |
dcterms.source.startPage | 218 | |
dcterms.source.endPage | 223 | |
dcterms.source.title | IEEE Int. Conf. on Multimedia & Expo | |
dcterms.source.series | IEEE Int. Conf. on Multimedia & Expo | |
dcterms.source.isbn | 9780769547114 | |
dcterms.source.conference | ICME 2012 | |
dcterms.source.conference-start-date | Jul 9 2012 | |
dcterms.source.conferencelocation | Melbourne | |
dcterms.source.place | Not known | |
curtin.department | ||
curtin.accessStatus | Open access |