2.50
Hdl Handle:
http://hdl.handle.net/10547/293038
Title:
Comparing robustness of pairwise and multiclass neural-network systems for face recognition
Authors:
Uglov, J.; Jakaite, Livija; Schetinin, Vitaly ( 0000-0003-1826-0153 ) ; Maple, Carsten
Abstract:
Noise, corruptions, and variations in face images can seriously hurt the performance of face-recognition systems. To make these systems robust to noise and corruptions in image data, multiclass neural networks capable of learning from noisy data have been suggested. However on large face datasets such systems cannot provide the robustness at a high level. In this paper, we explore a pairwise neural-network system as an alternative approach to improve the robustness of face recognition. In our experiments, the pairwise recognition system is shown to outperform the multiclass-recognition system in terms of the predictive accuracy on the test face images.
Citation:
Uglov, J., Jakaite, L., Schetinin, V. & Maple, C. (2008) 'Comparing robustness of pairwise and multiclass neural-network systems for face recognition', EURASIP Journal on Advances in Signal Processing, 2008 pp.64.
Journal:
EURASIP Journal on Advances in Signal Processing
Issue Date:
2008
URI:
http://hdl.handle.net/10547/293038
DOI:
10.1155/2008/468693
Additional Links:
http://asp.eurasipjournals.com/content/2008/1/468693
Type:
Article
Language:
en
ISSN:
1687-6180
Appears in Collections:
Centre for Research in Distributed Technologies (CREDIT)

Full metadata record

DC FieldValue Language
dc.contributor.authorUglov, J.en_GB
dc.contributor.authorJakaite, Livijaen_GB
dc.contributor.authorSchetinin, Vitalyen_GB
dc.contributor.authorMaple, Carstenen_GB
dc.date.accessioned2013-05-30T13:09:44Z-
dc.date.available2013-05-30T13:09:44Z-
dc.date.issued2008-
dc.identifier.citationUglov, J., Jakaite, L., Schetinin, V. & Maple, C. (2008) 'Comparing robustness of pairwise and multiclass neural-network systems for face recognition', EURASIP Journal on Advances in Signal Processing, 2008 pp.64.en_GB
dc.identifier.issn1687-6180-
dc.identifier.doi10.1155/2008/468693-
dc.identifier.urihttp://hdl.handle.net/10547/293038-
dc.description.abstractNoise, corruptions, and variations in face images can seriously hurt the performance of face-recognition systems. To make these systems robust to noise and corruptions in image data, multiclass neural networks capable of learning from noisy data have been suggested. However on large face datasets such systems cannot provide the robustness at a high level. In this paper, we explore a pairwise neural-network system as an alternative approach to improve the robustness of face recognition. In our experiments, the pairwise recognition system is shown to outperform the multiclass-recognition system in terms of the predictive accuracy on the test face images.en_GB
dc.language.isoenen
dc.relation.urlhttp://asp.eurasipjournals.com/content/2008/1/468693en_GB
dc.rightsArchived with thanks to EURASIP Journal on Advances in Signal Processingen_GB
dc.subjectG760 Machine Learningen_GB
dc.subjectface recognition systemsen_GB
dc.subjectface recognitionen_GB
dc.subjectneural networksen_GB
dc.subjectmulticlass-recognition systemen_GB
dc.subjectcorruptionsen_GB
dc.subjectnoiseen_GB
dc.titleComparing robustness of pairwise and multiclass neural-network systems for face recognitionen
dc.typeArticleen
dc.identifier.journalEURASIP Journal on Advances in Signal Processingen_GB
This item is licensed under a Creative Commons License
Creative Commons
All Items in UOBREP are protected by copyright, with all rights reserved, unless otherwise indicated.