Statistical transformations of frontal models for non-frontal face verification
Sanderson, C.
Bengio, S.
IDIAP Res. Inst., Martigny, Switzerland;
This paper appears in: Image Processing, 2004. ICIP '04. 2004 International Conference on
Publication Date: 24-27 Oct. 2004
Volume: 1,
On page(s): 585- 588 Vol. 1
ISSN: 1522-4880
ISBN: 0-7803-8554-3
INSPEC Accession Number: 8402630
Digital Object Identifier: 10.1109/ICIP.2004.1418822
Posted online: 2005-04-18 09:12:25.0
Abstract
In the framework of a face verification system using local features and a Gaussian mixture model based classifier, we address the problem of non-frontal face verification (when only a single (frontal) training image is available) by extending each client's frontal face model with artificially synthesized models for non-frontal views. Furthermore, we propose the maximum likelihood shift (MLS) synthesis technique and compare its performance against a maximum likelihood linear regression (MLLR) based technique (originally developed for adapting speech recognition systems) and the recently proposed "difference between two universal background models" (UBMdiff) technique. All techniques rely on prior information and learn how a generic face model for the frontal view is related to generic models at non-frontal views. Experiments on the FERET database suggest that that the proposed MLS technique is more suitable than MLLR (due to a lower number of free parameters) and UBMdiff (due to lack of heuristics). The results further suggest that extending frontal models considerably reduces errors.
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
