Artículos de revistas
Robustness of multimodal biometric fusion methods against spoof attacks
Registro en:
Journal Of Visual Languages And Computing. Academic Press Ltd- Elsevier Science Ltd, v. 20, n. 3, n. 169, n. 179, 2009.
1045-926X
WOS:000266347300005
10.1016/j.jvlc.2009.01.010
Autor
Rodrigues, RN
Ling, LL
Govindaraju, V
Institución
Resumen
In this paper, we address,the security of multimodal biometric systems when one of the modes is successfully spoofed. We propose two novel fusion schemes that can increase the security of multimodal biometric systems. The first is an extension of the likelihood ratio based fusion scheme and the other uses fuzzy logic. Besides the matching score and sample quality score, our proposed fusion schemes also take into account the intrinsic security of each biometric system being fused. Experimental results have shown that the proposed methods are more robust against spoof attacks when compared with traditional fusion methods. (c) 2009 Elsevier Ltd. All rights reserved. 20 3 169 179