Full Video Processing for Mobile Audio-Visual Identity Verification

Alexander Usoltsev, Dijana Petrovska-Delacrétaz, Khemiri Houssemeddine

2016

Abstract

This paper describes a bi-modal biometric verification system based on voice and face modalities, which takes advantage of the full video processing instead of using still-images. The bi-modal system is evaluated on the MOBIO corpus and results show a relative improvement of performance by nearly 10% when the whole video is used. The fusion between face and speaker verification systems, using linear logistic regression weights, gives a relative improvement of performance that varies between 30% and 60% comparing to the best uni-modal system. Proof-of-concept iPad application is developed based on the proposed bi-modal system.

Paper Citation

in Harvard Style

Usoltsev A., Petrovska-Delacrétaz D. and Houssemeddine K. (2016). Full Video Processing for Mobile Audio-Visual Identity Verification . In Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-173-1, pages 552-557. DOI: 10.5220/0005667305520557

in Bibtex Style

@conference{icpram16,
author={Alexander Usoltsev and Dijana Petrovska-Delacrétaz and Khemiri Houssemeddine},
title={Full Video Processing for Mobile Audio-Visual Identity Verification},
booktitle={Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2016},
pages={552-557},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005667305520557},
isbn={978-989-758-173-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Full Video Processing for Mobile Audio-Visual Identity Verification
SN - 978-989-758-173-1
AU - Usoltsev A.
AU - Petrovska-Delacrétaz D.
AU - Houssemeddine K.
PY - 2016
SP - 552
EP - 557
DO - 10.5220/0005667305520557