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.
|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|
|Number of pages||8|
|Publication status||Published - 1 Apr 2006|
|Event||MMUI2005 - Sydney, Australia|
Duration: 13 Sep 2005 → 14 Sep 2005
|Period||13/09/05 → 14/09/05|
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, pp. 17-24). Australia: Australian Computer Society.