International Journal of Biometrics
Multimodal biometric score fusion using Gaussian mixture model and Monte Carlo method
Journal of Computer Science and Technology
| Hi-index | 0.00 |
Multimodal biometrics has drawn lot of attention in recent days as it provides more reliable scheme for person verification. Multimodal biometrics includes the fusion of information from different modalities. This paper presents a novel method for assigning weights before performing fusion at match score level. The proposed method is based on False Acceptance Rate (FAR) and Genuine Acceptance Rate (GAR) obtained for each modality and weights are assigned on match scores of individual modality before performing match score level fusion. Extensive experiments carried out on three different build multimodal biometric databases shows the efficacy of the proposed method