Catalog Home Page

Audio-visual biometric recognition via joint sparse representations

Primorac, R., Togneri, R., Bennamoun, M. and Sohel, F. (2016) Audio-visual biometric recognition via joint sparse representations. In: 2016 23rd International Conference on Pattern Recognition (ICPR), 4-8 Dec. 2016 pp. 3031-3035.

Link to Published Version: https://doi.org/10.1109/ICPR.2016.7900099
*Subscription may be required

Abstract

In this paper we present a novel audio-visual (AV) person identification system based on joint sparse representation. Video features used were vectorized raw pixel values, while i-vectors were used as the audio features. Classification is performed by solving the joint sparsity optimization problem, and fusion is carried out by using the quality (confidence) assigned to each matcher. Our experimental results on the challenging MOBIO database using 100 subjects show that the system based on joint sparse representation outperforms the system based on separate sparse representations for each modality. Furthermore, we show that our newly introduced quality measure improves the system's performance, when compared to conventionally used quality measures for sparse representation - based systems.

Publication Type: Conference Paper
Murdoch Affiliation: School of Engineering and Information Technology
Publisher: Institute of Electrical and Electronics Engineers Inc.
Copyright: © 2016 IEEE.
URI: http://researchrepository.murdoch.edu.au/id/eprint/36773
Item Control Page Item Control Page