Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{189899,
        author = {P ARUNA KUMARI},
        title = {Multi-Algorithm Biometric Person Authentication using Particle Swarm Optimization: Feature Selection for Enhanced Security and Reduced Computational Complexity},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {8},
        pages = {77-86},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189899},
        abstract = {multi-algorithm biometric systems consolidate information from multiple feature extraction algorithms applied to single biometric traits, providing robust authentication without additional sensor overhead. This paper presents a comprehensive framework for multi-algorithm biometric person authentication using basic Particle Swarm Optimization (PSO) for optimal feature selection at the feature-level fusion stage. The study systematically applies PSO to fingerprint, iris, and palmprint multi-algorithm systems using standard PSO formulation with velocity-based position updates and binary discretization. Experimental validation on benchmark databases (CASIA, IITD, FVC) demonstrates that basic PSO achieves 94-97% recognition accuracy with 80-88% feature space reduction using Euclidean distance matching and up to 96-97% accuracy with supervised classifiers (C4.5, SMO). The approach outperforms traditional dimensionality reduction methods (PCA) with 10-15% accuracy improvements while maintaining comparable feature reduction ratios. Computational analysis shows PSO requires 50-60 seconds for feature selection (one-time offline cost) with acceptable testing time (0.08 seconds), enabling practical deployment in real-time biometric authentication systems. The paper provides detailed implementation specifications, extensive experimental validation across multiple classifiers, and practical insights for PSO-based feature selection in biometric systems.},
        keywords = {Biometric authentication, feature selection, particle swarm optimization, multi-algorithm systems, feature-level fusion, dimensionality reduction, fingerprint, iris, palmprint.},
        month = {December},
        }