Multimodel biometrics Fusion based on FAR and FRR using Triangular Norm

Abstract

Multibiomitric systems are expected to be more accurate due to the presence of multiple evidences, score level fusion is the most commonly used approach in multibiometrics. In this paper, A novel approach is proposed for the fusion at score level fusion based on False Reject Rate(FRR) and False Accept Rate(FRR) using triangular norms(t-norms). This study aims at tapping the potential of t-norms for information fusion at first, at the second, it transfers scores into Transfer function based on corresponding FRRs and FARs, thus avoiding calculating posterior probability of a certain score. Experiment result shown that the proposed method renders very good performance as it is quite computationally and outperforms the traditional score level fusion schemes, the experimental result also confirms the effectiveness of the proposed method to improve the performance of multibiometric system.

Multimodal biometrics Fusion based on TER and Hybrid Intelligent Multiple Hidden Layer Probabilistic Extreme Learning Machine

“…In conclusion, the transformation-based fusion approach, with no training process and few consideration of distribution of matching scores and it is easy to implement [7]. On the contrary, density-based fusion method, which requires accurate estimation of density and huge number of training samples, is hard to carry out for the following reasons: firstly, positive samples, namely genuine matching scores are limited in today's multi-biometric systems, secondly, it is difficult to estimate the density of matching scores in that they may not obey a certain distribution model.…”