Publication Details

On the Results of the First Mobile Biometry (MOBIO) Face and Speaker Verification Evaluation

MARCEL, S.; MCCOOL, C.; MATĚJKA, P.; ČERNOCKÝ, J.; KITTLER, J.; GLEMBEK, O.; PLCHOT, O.; JANČÍK, Z.; LARCHER, A.; LÉVY, C. On the Results of the First Mobile Biometry (MOBIO) Face and Speaker Verification Evaluation. In Recognizing Patterns in Signals, Speech, Images, and Videos. Lecture Notes in Computer Science. Lecture Notes in Computer Science. Istanbul: Springer Verlag, 2010. p. 210-225. ISBN: 978-3-642-17710-1. ISSN: 0302-9743.
Czech title
O výsledcích evaluace první mobilní biometrie obličeje a verifikace mluvčího (MOBIO)
Type
conference paper
Language
English
Authors
Marcel Sebastien
McCool Christopher
Matějka Pavel, Ing., Ph.D. (DCGM)
Černocký Jan, prof. Dr. Ing. (DCGM)
Kittler Josef, prof.
Glembek Ondřej, Ing., Ph.D.
Plchot Oldřich, Ing., Ph.D. (DCGM)
Jančík Zdeněk, Ing.
Larcher Anthony
Lévy Christophe
and others
URL
Keywords

mobile, biometric, face recognition, speaker recognition, evaluation

Abstract

This paper presents the results of several uni-modal face and speaker verification techniques on the MOBIO database. This database provides realistic and challenging conditions as it was captured on a mobile device and in uncontrolled environments.

Annotation

This paper evaluates the performance of face and speaker verification techniques in the context of a mobile environment. The mobile environment was chosen as it provides a realistic and challenging test-bed for biometric person verification techniques to operate. For instance the audio environment is quite noisy and there is limited control over the illumination conditions and the pose of the subject for the video. To conduct this evaluation, a part of a database captured during the "Mobile Biometry" (MOBIO) European Project was used. In total there were nine participants to the evaluation who submitted a face verification system and five participants who submitted speaker verification systems. The results have shown that the best performing face and speaker verification systems obtained the same level of performance, respectively 10.9% and 10.6% of HTER.

Published
2010
Pages
210–225
Journal
Lecture Notes in Computer Science, vol. 6388, no. 08, ISSN 0302-9743
Proceedings
Recognizing Patterns in Signals, Speech, Images, and Videos
Series
Lecture Notes in Computer Science
ISBN
978-3-642-17710-1
Publisher
Springer Verlag
Place
Istanbul
DOI
EID Scopus
BibTeX
@inproceedings{BUT76264,
  author="Sebastien {Marcel} and Christopher {McCool} and Pavel {Matějka} and Jan {Černocký} and Josef {Kittler} and Ondřej {Glembek} and Oldřich {Plchot} and Zdeněk {Jančík} and Anthony {Larcher} and Christophe {Lévy}",
  title="On the Results of the First Mobile Biometry (MOBIO) Face and Speaker Verification Evaluation",
  booktitle="Recognizing Patterns in Signals, Speech, Images, and Videos",
  year="2010",
  series="Lecture Notes in Computer Science",
  journal="Lecture Notes in Computer Science",
  volume="6388",
  number="08",
  pages="210--225",
  publisher="Springer Verlag",
  address="Istanbul",
  doi="10.1007/978-3-642-17711-8\{_}22",
  isbn="978-3-642-17710-1",
  issn="0302-9743",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2010/matejka_ICPR_Turkey_2010.pdf"
}
Back to top