Score Fusion in Multibiometric Identification Based on Fuzzy Set Theory

摘要

Multimodal biometric systems consolidate or fuse information from multiple biometric sources. They have been developed to overcome several limitations of each individual biometric system, such as sensitivity to noise, intra class invariability, data quality, non-universality and other factors. In this paper, we propose a general framework of multibiometric identification system based on fusion at matching score level using fuzzy set theory. The motivation for using fuzzy set theory is that it offers methods suited to treat (modeling, fusion,...) and take into account the information inherently uncertain and ambiguous. We note that our fusion system is based on face and iris modalities. Experimental results exhibit that the proposed method performance bring obvious improvement compared to unimodal biometric identification methods and classical combination approaches at score level fusion.