Audio-Visual Multimodal Fusion for Biometric Person Authentication and Liveness Verification

Girija Chetty; Michael Wagner

Audio-Visual Multimodal Fusion for Biometric Person Authentication and Liveness Verification

Information Systems

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

Abstract

In this paper we propose a multimodal fusion framework based on novel face-voice fusion techniques for biometric person authentication and liveness verification. Checking liveness guards the system against spoof/replay attacks by ensuring that the biometric data is captured from an authorised live person. The proposed framework based on bi-modal feature fusion, cross-modal fusion as well as 3D shape and texture fusion techniques, allow a significant improvement in system performance against impostor attacks, type-1 replay attacks (still photo and prerecorded audio), and challenging type-2 replay attacks(CG animated video from a still photo and pre-recorded audio) and robustness to pose and illumination variations.

Original language	English
Title of host publication	MMUI '05: Proceedings of the 2005 NICTA
Subtitle of host publication	HCSNet Multimodal User Interaction Workshop - Volume 57
Editors	Fang Chen, Julien Epps
Place of Publication	Australia
Publisher	Australian Computer Society
Pages	17-24
Number of pages	8
Volume	57
ISBN (Print)	1920682392
Publication status	Published - 1 Apr 2006
Event	MMUI2005 - Sydney, Australia Duration: 13 Sept 2005 → 14 Sept 2005

Conference

Conference	MMUI2005
Country/Territory	Australia
City	Sydney
Period	13/09/05 → 14/09/05

Access to Document

https://dl.acm.org/doi/abs/10.5555/1151804.1151808

Cite this

@inproceedings{3d852538a2974ed5875f56801e3d875e,

title = "Audio-Visual Multimodal Fusion for Biometric Person Authentication and Liveness Verification",

abstract = "In this paper we propose a multimodal fusion framework based on novel face-voice fusion techniques for biometric person authentication and liveness verification. Checking liveness guards the system against spoof/replay attacks by ensuring that the biometric data is captured from an authorised live person. The proposed framework based on bi-modal feature fusion, cross-modal fusion as well as 3D shape and texture fusion techniques, allow a significant improvement in system performance against impostor attacks, type-1 replay attacks (still photo and prerecorded audio), and challenging type-2 replay attacks(CG animated video from a still photo and pre-recorded audio) and robustness to pose and illumination variations.",

author = "Girija Chetty and Michael Wagner",

year = "2006",

month = apr,

day = "1",

language = "English",

isbn = "1920682392",

volume = "57",

pages = "17--24",

editor = "Fang Chen and Julien Epps",

booktitle = "MMUI '05: Proceedings of the 2005 NICTA",

publisher = "Australian Computer Society",

address = "Australia",

note = "MMUI2005 ; Conference date: 13-09-2005 Through 14-09-2005",

}

Chetty, G & Wagner, M 2006, Audio-Visual Multimodal Fusion for Biometric Person Authentication and Liveness Verification. in F Chen & J Epps (eds), MMUI '05: Proceedings of the 2005 NICTA: HCSNet Multimodal User Interaction Workshop - Volume 57. vol. 57, Australian Computer Society, Australia, pp. 17-24, MMUI2005, Sydney, Australia, 13/09/05. <https://dl.acm.org/doi/abs/10.5555/1151804.1151808>

Audio-Visual Multimodal Fusion for Biometric Person Authentication and Liveness Verification. / Chetty, Girija; Wagner, Michael.
MMUI '05: Proceedings of the 2005 NICTA: HCSNet Multimodal User Interaction Workshop - Volume 57. ed. / Fang Chen; Julien Epps. Vol. 57 Australia: Australian Computer Society, 2006. p. 17-24.

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

TY - GEN

T1 - Audio-Visual Multimodal Fusion for Biometric Person Authentication and Liveness Verification

AU - Chetty, Girija

AU - Wagner, Michael

PY - 2006/4/1

Y1 - 2006/4/1

N2 - In this paper we propose a multimodal fusion framework based on novel face-voice fusion techniques for biometric person authentication and liveness verification. Checking liveness guards the system against spoof/replay attacks by ensuring that the biometric data is captured from an authorised live person. The proposed framework based on bi-modal feature fusion, cross-modal fusion as well as 3D shape and texture fusion techniques, allow a significant improvement in system performance against impostor attacks, type-1 replay attacks (still photo and prerecorded audio), and challenging type-2 replay attacks(CG animated video from a still photo and pre-recorded audio) and robustness to pose and illumination variations.

AB - In this paper we propose a multimodal fusion framework based on novel face-voice fusion techniques for biometric person authentication and liveness verification. Checking liveness guards the system against spoof/replay attacks by ensuring that the biometric data is captured from an authorised live person. The proposed framework based on bi-modal feature fusion, cross-modal fusion as well as 3D shape and texture fusion techniques, allow a significant improvement in system performance against impostor attacks, type-1 replay attacks (still photo and prerecorded audio), and challenging type-2 replay attacks(CG animated video from a still photo and pre-recorded audio) and robustness to pose and illumination variations.

M3 - Conference contribution

SN - 1920682392

VL - 57

SP - 17

EP - 24

BT - MMUI '05: Proceedings of the 2005 NICTA

A2 - Chen, Fang

A2 - Epps, Julien

PB - Australian Computer Society

CY - Australia

T2 - MMUI2005

Y2 - 13 September 2005 through 14 September 2005

ER -

Audio-Visual Multimodal Fusion for Biometric Person Authentication and Liveness Verification

Abstract

Conference

Access to Document

Fingerprint

Cite this