Multimodal biometric identification system based on the face and iris

The multimodal biometric systems make use of two or more modalities that together achieve much higher performances to overcome the defects of the unimodal biometric system. Depending on the application context, biometrics recognition system may be used either to identification or in the verification of an individual. This paper proposes multimodal biometric system based on the face and iris operate in identification mode. The fusion is applied at the matching score level, with various normalization and fusion rule. A large-scale dataset is investigated to validate the proposed scheme, using the face ORL database and CASIA-V3-Interval database. The experimental results showed that the proposed multimodal biometric identification system achieves high recognition rate.