Show simple item record

dc.contributor.authorSanderson, C
dc.contributor.authorBengio, S
dc.date.accessioned2020-07-30T04:03:39Z
dc.date.available2020-07-30T04:03:39Z
dc.date.issued2004
dc.identifier.isbn0780385543
dc.identifier.doi10.1109/icip.2004.1418822
dc.identifier.urihttp://hdl.handle.net/10072/395922
dc.description.abstractIn 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.
dc.publisherIEEE
dc.relation.ispartofconferencename2004 International Conference on Image Processing, 2004. ICIP '04
dc.relation.ispartofconferencetitle2004 International Conference on Image Processing, 2004. ICIP '04
dc.relation.ispartofdatefrom2004-10-24
dc.relation.ispartofdateto2004-10-27
dc.relation.ispartofpagefrom585
dc.relation.ispartofpageto588
dc.titleStatistical transformations of frontal models for non-frontal face verification
dc.typeConference output
dcterms.bibliographicCitationSanderson, C; Bengio, S, Statistical transformations of frontal models for non-frontal face verification, 2004 International Conference on Image Processing, 2004. ICIP '04, pp. 585-588
dc.date.updated2020-07-29T06:43:59Z
dc.description.versionAccepted Manuscript (AM)
gro.rights.copyright© 2004 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
gro.hasfulltextFull Text
gro.griffith.authorSanderson, Conrad


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record