Multimodal Biometric Authentication System using Probabilistic Fuzzy based Tuna Search Optimization

The biometric system plays a maj or role in data security with better growth rate. The multimodal biometric system with better accuracy and the rate of recognition still acts as the challenging issue. So, this research introduced probabilistic fuzzy based Tuna Search Optimization (TSO) to recognize the biometrics with score level fusion. Initially, the data is acquisitioned and the pre-processing is performed on both the samples of fingerprint and iris. The features from the processed output is extracted and provided as input for the stage of score level fusion. The efficiency of the proposed approach is evaluated by means of False Acceptance Rate (FAR), False Rejection Rate (FRR), accuracy and equal error rate. The experimental results show that the proposed approach achieved better results in overall metrics when it is compared with the existing techniques. The accuracy of the proposed approach is 99.96% which is comparably higher than the existing approaches such as adaptive fuzzy genetic algorithm, modified relief feature selection and multi-support vector machine and optimized fuzzy genetic algorithm with accuracies of 96%, 97% and 99.83 % respectively.