A new look at filtering techniques for illumination invariance in automatic face recognition Arandjelovic, Ognjen and Cipolla, R. 2006, A new look at filtering techniques for illumination invariance in automatic face recognition, in FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition 2006, IEEE, Piscataway, New Jersey, pp. 449-454, doi: 10.1109/FGR.2006.14. Attached Files Name Description MIMEType Size Downloads arandjelovic-newlook-2006.pdf Published version application/pdf 1.05MB 240 Title A new look at filtering techniques for illumination invariance in automatic face recognition Author(s) Arandjelovic, Ognjen Cipolla, R. Conference name International Conference on Automatic Face & Gesture Recognition (7th : 2006 : Amsterdam, The Netherlands) Conference location Southampton, England Conference dates 2-6 April 2006 Title of proceedings FGR 2006: Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition 2006 Editor(s) [Unknown] Publication date 2006 Conference series Automatic Face and Gesture Recognition Conference Start page 449 End page 454 Total pages 6 Publisher IEEE Place of publication Piscataway, New Jersey Keyword(s) image processing filters illumination conditions algorithms Summary Illumination invariance remains the most researched, yet the most challenging aspect of automatic face recognition. In this paper we propose a novel, general recognition framework for efficient matching of individual face images, sets or sequences. The framework is based on simple image processing filters that compete with unprocessed greyscale input to yield a single matching score between individuals. It is shown how the discrepancy between illumination conditions between novel input and the training data set can be estimated and used to weigh the contribution of two competing representations. We describe an extensive empirical evaluation of the proposed method on 171 individuals and over 1300 video sequences with extreme illumination, pose and head motion variation. On this challenging data set our algorithm consistently demonstrated a dramatic performance improvement over traditional filtering approaches. We demonstrate a reduction of 50-75% in recognition error rates, the best performing method-filter combination correctly recognizing 96% of the individuals. ISBN 0769525032 9780769525037 Language eng DOI 10.1109/FGR.2006.14 Field of Research 080104 Computer Vision 080106 Image Processing 080109 Pattern Recognition and Data Mining Socio Economic Objective 890205 Information Processing Services (incl. Data Entry and Capture) HERDC Research category E1.1 Full written paper - refereed Copyright notice ©2006, IEEE Free to Read? Yes Persistent URL http://hdl.handle.net/10536/DRO/DU:30058441 Document type: Conference Paper Collections: Faculty of Science, Engineering and Built Environment Centre for Pattern Recognition and Data Analytics (PRADA) Open Access Collection Related Links Link Description Connect to published version (restricted access) Go to link with your DU access privileges     Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved. Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au. Versions Version Filter Type Tue, 26 Nov 2013, 12:54:14 EST Tue, 26 Nov 2013, 13:34:10 EST Fri, 24 Jan 2014, 10:26:54 EST Tue, 17 Nov 2015, 14:13:28 EST Tue, 06 Sep 2016, 22:07:28 EST Tue, 05 Dec 2017, 12:44:54 EST Fri, 07 Sep 2018, 16:48:39 EST Filtered Full Citation counts:   Cited 0 times in TR Web of Science Cited 0 times in Scopus Search Google Scholar Access Statistics: 188 Abstract Views, 240 File Downloads  -  Detailed Statistics Created: Tue, 26 Nov 2013, 12:54:14 EST