International Journal of Advanced Research in Computer Science and Software Engineering (IJARCSSE)
Mulimodal biometrics is more robust and secures then unimodal biometrics. In multimodal fusion at feature level is considered more effective as a wide raw feature set is available and can be manipulated as per requirement. This paper focuses on fusion of fingerprint and iris biometrics at feature level. The proposed approach is based on the fusion of the traits by extracting independent features from the respective modalities. So far there has been extensive work done on fusion at the match score, sensor level, decision level but fusion of the feature level in heterogeneous environment is still an understudied problem.