Deakin home > Deakin University Library > Deakin Research Online > Learning Boltzmann distance metric for face recognition

Learning Boltzmann distance metric for face recognition

Tran, Truyen, Phung, Dinh Q. and Venkatesh, Svetha 2012, Learning Boltzmann distance metric for face recognition, in ICME 2012 : Proceedings of the 13th IEEE International Conference on Multimedia and Expo, IEEE, Piscataway, N.J., pp. 218-223.

Attached Files (Some files may be inaccessible until you login with your Deakin Research Online credentials)
Name Description MIMEType Size Downloads

Title Learning Boltzmann distance metric for face recognition
Author(s) Tran, Truyen
Phung, Dinh Q.
Venkatesh, Svetha
Conference name IEEE Multimedia and Expo Conference (13th : 2012 : Melbourne, Victoria)
Conference location Melbourne, Victoria
Conference dates 9-13 Jul. 2012
Title of proceedings ICME 2012 : Proceedings of the 13th IEEE International Conference on Multimedia and Expo
Editor(s) [Unknown]
Publication date 2012
Conference series IEEE Multimedia and Expo Conference
Start page 218
End page 223
Total pages 6
Publisher IEEE
Place of publication Piscataway, N.J.
Keyword(s) face recognition
information fusion
metric learning
Restricted Boltzmann Machines
Summary 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 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.
ISBN 9780769547114
Language eng
Field of Research 089999 Information and Computing Sciences not elsewhere classified
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category E1 Full written paper - refereed
Persistent URL http://hdl.handle.net/10536/DRO/DU:30051374

Document type: Conference Paper
Collection: Centre for Pattern Recognition and Data Analytics
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in Deakin Research Online is owned by the author, with all rights reserved.

Versions
Version Filter Type
Access Statistics: 20 Abstract Views, 2 File Downloads  -  Detailed Statistics
Created: Mon, 18 Mar 2013, 09:43:26 EST