Multimodal Biometrics Recognition by using Modified Unconstrained Cohort Normalisation under Unconstrained Setting

Objective: The main intention of this research is to provide secured authentication on mobile devices with the use of multimodal based biometric authentication system under unconstrained settings. Methods: Method used in this research is pattern recognition algorithm namely modified unconstrained cohort normalisation (MUCN) is introduced into the score-level fusion process of multi-biometric system. The goal of proposed MUCN is normalizing the unconstraint modalities by correcting the misclassified scores occur in the UCN. Score normalization of multimodal biometric is enhanced and investigated for improving the accuracy performance of the multimodal biometric in an unconstraint setting. Results: The result of presented pattern recognition algorithm performs well in terms of recognition accuracy when compared to existing schemes.From the comparative evaluation on WVU multimodal data set, the proposed MUCN based Score level fusion achieves 89.2 % of overall recognition rate and out-performs existing state-of-art techniques. Conclusion: The present work demonstrates that the result obtained by MUCN can considerably improve the accuracy of fused biometrics. Thus it can be concluded that with respect to the obtained comparison results from the experiment, the proposed method provides highest recognization rate when compare with other conventional methods of biometric recognition system.