Generalized joint sparse representation for multimodal biometric fusion of heterogeneous features

Rudi Primorac; Roberto Togneri; Mohammed Bennamoun; Ferdous Sohel

doi:10.1109/WIFS.2018.8630775

Generalized joint sparse representation for multimodal biometric fusion of heterogeneous features

Rudi Primorac, Roberto Togneri, Mohammed Bennamoun, Ferdous Sohel

Research output: Chapter in Book/Conference paper › Conference paper

1 Citation (Scopus)

Abstract

In this paper we introduce a novel multimodal biometric recognition system based on generalized sparse representations. In the recently proposed systems, with heterogeneous features (such as audio and video), the joint sparse optimization problem was addressed by bringing the features into the same dynamic range, such as normalizing the features into unitl2 norm. This is however not optimal, and such normalization may decrease the performance of that modality unimodally. We propose to solve the original joint sparse optimization problem by introducing scaling factors for different modalities, such that the modalities interact efficiently at the feature level. The sequence-dependent scaling factors are automatically calculated so that the mismatch between the sparse representations of different modalities is accounted for. In the case of audiovisual recognition system, our experiments on the challenging MOBIO database show that the proposed method outperforms the original joint sparsity-based system (96.8% vs 94.3% recognition rate). © 2018 IEEE.

Original language	English
Title of host publication	2018 IEEE International Workshop on Information Forensics and Security (WIFS)
Place of Publication	USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
DOIs	https://doi.org/10.1109/WIFS.2018.8630775
Publication status	Published - 30 Jan 2019
Event	2018 IEEE International Workshop on Information Forensics and Security - Hong Kong , China Duration: 11 Dec 2018 → 13 Dec 2018 https://wifs2018.comp.polyu.edu.hk/ https://signalprocessingsociety.org/blog/wifs-2018-2018-ieee-international-workshop-information-forensics-and-security

Conference

Conference	2018 IEEE International Workshop on Information Forensics and Security
Abbreviated title	WIFS 2018
Country	China
City	Hong Kong
Period	11/12/18 → 13/12/18
Other	IEEE International Workshop on Information Forensics and Security (WIFS) is a unique annual event which is technically co-sponsored by the IEEE Biometrics Council and IEEE Signal Processing Society. The 2018 edition of this workshop will be held in Hong Kong. WIFS is the unique workshop series organised by the IEEE Information Forensics and Security (IFS) Technical Committee of the IEEE Signal Processing Society. It's a major forum that brings researchers from related disciplines to discuss emerging challenges in different areas of information security and forensics, and share the latest results. This workshop serves to provide a high quality forum for advancing research and development efforts in a range of areas defining e-security and forensics.
Internet address	https://wifs2018.comp.polyu.edu.hk/ https://signalprocessingsociety.org/blog/wifs-2018-2018-ieee-international-workshop-information-forensics-and-security

Access to Document

10.1109/WIFS.2018.8630775

Fingerprint Dive into the research topics of 'Generalized joint sparse representation for multimodal biometric fusion of heterogeneous features'. Together they form a unique fingerprint.

Cite this

@inproceedings{2651422ff9bf47858b6f6e444bd2d380,

title = "Generalized joint sparse representation for multimodal biometric fusion of heterogeneous features",

abstract = "In this paper we introduce a novel multimodal biometric recognition system based on generalized sparse representations. In the recently proposed systems, with heterogeneous features (such as audio and video), the joint sparse optimization problem was addressed by bringing the features into the same dynamic range, such as normalizing the features into unitl2 norm. This is however not optimal, and such normalization may decrease the performance of that modality unimodally. We propose to solve the original joint sparse optimization problem by introducing scaling factors for different modalities, such that the modalities interact efficiently at the feature level. The sequence-dependent scaling factors are automatically calculated so that the mismatch between the sparse representations of different modalities is accounted for. In the case of audiovisual recognition system, our experiments on the challenging MOBIO database show that the proposed method outperforms the original joint sparsity-based system (96.8% vs 94.3% recognition rate). {\textcopyright} 2018 IEEE.",

author = "Rudi Primorac and Roberto Togneri and Mohammed Bennamoun and Ferdous Sohel",

year = "2019",

month = jan,

day = "30",

doi = "10.1109/WIFS.2018.8630775",

language = "English",

booktitle = "2018 IEEE International Workshop on Information Forensics and Security (WIFS)",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

note = "2018 IEEE International Workshop on Information Forensics and Security, WIFS 2018 ; Conference date: 11-12-2018 Through 13-12-2018",

url = "https://wifs2018.comp.polyu.edu.hk/, https://signalprocessingsociety.org/blog/wifs-2018-2018-ieee-international-workshop-information-forensics-and-security",

}

Primorac, R, Togneri, R , Bennamoun, M & Sohel, F 2019, Generalized joint sparse representation for multimodal biometric fusion of heterogeneous features. in 2018 IEEE International Workshop on Information Forensics and Security (WIFS)., 8630775, IEEE, Institute of Electrical and Electronics Engineers, USA, 2018 IEEE International Workshop on Information Forensics and Security, Hong Kong , China, 11/12/18. https://doi.org/10.1109/WIFS.2018.8630775

Generalized joint sparse representation for multimodal biometric fusion of heterogeneous features. / Primorac, Rudi; Togneri, Roberto ; Bennamoun, Mohammed ; Sohel, Ferdous.

2018 IEEE International Workshop on Information Forensics and Security (WIFS). USA : IEEE, Institute of Electrical and Electronics Engineers, 2019. 8630775.

Research output: Chapter in Book/Conference paper › Conference paper

TY - GEN

T1 - Generalized joint sparse representation for multimodal biometric fusion of heterogeneous features

AU - Primorac, Rudi

AU - Togneri, Roberto

AU - Bennamoun, Mohammed

AU - Sohel, Ferdous

PY - 2019/1/30

Y1 - 2019/1/30

N2 - In this paper we introduce a novel multimodal biometric recognition system based on generalized sparse representations. In the recently proposed systems, with heterogeneous features (such as audio and video), the joint sparse optimization problem was addressed by bringing the features into the same dynamic range, such as normalizing the features into unitl2 norm. This is however not optimal, and such normalization may decrease the performance of that modality unimodally. We propose to solve the original joint sparse optimization problem by introducing scaling factors for different modalities, such that the modalities interact efficiently at the feature level. The sequence-dependent scaling factors are automatically calculated so that the mismatch between the sparse representations of different modalities is accounted for. In the case of audiovisual recognition system, our experiments on the challenging MOBIO database show that the proposed method outperforms the original joint sparsity-based system (96.8% vs 94.3% recognition rate). © 2018 IEEE.

AB - In this paper we introduce a novel multimodal biometric recognition system based on generalized sparse representations. In the recently proposed systems, with heterogeneous features (such as audio and video), the joint sparse optimization problem was addressed by bringing the features into the same dynamic range, such as normalizing the features into unitl2 norm. This is however not optimal, and such normalization may decrease the performance of that modality unimodally. We propose to solve the original joint sparse optimization problem by introducing scaling factors for different modalities, such that the modalities interact efficiently at the feature level. The sequence-dependent scaling factors are automatically calculated so that the mismatch between the sparse representations of different modalities is accounted for. In the case of audiovisual recognition system, our experiments on the challenging MOBIO database show that the proposed method outperforms the original joint sparsity-based system (96.8% vs 94.3% recognition rate). © 2018 IEEE.

UR - http://www.scopus.com/inward/record.url?scp=85062837829&partnerID=8YFLogxK

UR - https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=5

U2 - 10.1109/WIFS.2018.8630775

DO - 10.1109/WIFS.2018.8630775

M3 - Conference paper

BT - 2018 IEEE International Workshop on Information Forensics and Security (WIFS)

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - USA

T2 - 2018 IEEE International Workshop on Information Forensics and Security

Y2 - 11 December 2018 through 13 December 2018

ER -