Enhancing Multimodal Biometric Recognition Using Whale Optimization Algorithm and Feedforward Neural Networks

Abstract

This paper presents a robust multimodal biometric recognition system that integrates fingerprint and iris recognition, utilizing the Whale Optimization Algorithm to enhance performance. The Feedforward Neural Networks ensure high accuracy for effective feature classification from both biometric modalities. The WOA system optimizes neural network parameters, concentrating on the most significant characteristics of the fingerprint and iris data. Experimental results indicate that the proposed system achieves a 99.6% accuracy, with minimal false acceptance and rejection rates. This makes it highly suitable for real-world applications such as secure access control, identity verification, and fraud detection. The integration of multiple biometric traits is not only security. But also improves the performance accuracy. This research highlights the potential of combining multimodal biometric systems with advanced neural network architectures and optimization techniques to create more secure and efficient biometric authentication solutions across various fields.