A Computational Approach for Score-Level Fusion Decision-Making of Multi-biometric Recognition System Using Ant Colony Optimisation

Abstract

This study presents a novel deep learning approach for improving the performance of a multi-biometric recognition system using Ant Colony Optimisation (ACO) at the score level. The proposed method integrates three biometric characteristics, the face, palm, and iris, into a single recognition input. A deep learning model, convolutional neural networks (CNNs), is employed to extract discriminative features from each attribute. The ACO algorithm optimizes the score-level fusion procedure, in which recognition scores from the combined input are combined to make the final determination. The experimental results show the method's efficacy in selecting the score level fusion method per the input biometric and implementation parameters. The ACO-based score-level fusion improves system performance by leveraging complementary information from multiple biometric characteristics, providing a promising solution for robust and accurate multi-biometric recognition in various applications, including access control and identity verification.