A New Hybrid Approach for Information Fusion in Multibiometric Systems

This paper proposes a new hybrid approach to verification aspect of a multibiometric system. This also gives a comparative analysis with traditional approaches such as multialgorithmic and multimodal versions of the same. For evaluating the performance we have considered different level of fusion with different fusion strategies for all the approaches, we have also calculated average EER to compare. Results from the experiments allow us to claim that the proposed hybrid approach performs better than traditional approaches and also consumes optimal number of modalities.