T. Tran, D.Q. Phung, and S. Venkatesh. Learning Boltzmann distance metric for face recognition. In Proc. of IEEE International Conference on Multimedia & Expo (ICME), Melbourne, Australia, 2012.

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 informationtheoretic 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 whole-face pixels to 99.2 feature extractors and appropriate resolutions.

[ bib .pdf  ]