Copyright © 2026 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{189878,
        author = {P ARUNA KUMARI},
        title = {Multi-Algorithm Biometric Person Authentication Using Artificial Bee Colony Based Feature Selection},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {7595-7610},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189878},
        abstract = {Multimodal biometric systems enhance person authentication by combining complementary information from multiple traits to overcome the limitations of unimodal systems such as noisy data, spoof attacks, intra-class variations, and non-universality [1][2].  In this work, a multi-algorithm feature-level fusion framework is proposed using fingerprint, iris, and palmprint modalities, where multiple feature extractors per trait are integrated into a common high-dimensional feature space [3][4]. To address the dimensionality problem and improve recognition accuracy, a basic Artificial Bee Colony (ABC) algorithm is employed as a wrapper-based feature selection method driven by a classification-based fitness function [5]. The binary ABC mechanism, employing employed bees, onlooker bees, and scout bees’ phases, effectively identifies the most discriminative feature subsets while reducing computational complexity [6]. Experimental evaluation on publicly available CASIA, IITD, and FVC benchmark databases demonstrates that the proposed ABC-based multi-algorithm system attains high recognition accuracy (96.5% 97.5% with Euclidean distance, 99% 99.4% with supervised classifiers) with significantly reduced feature dimension (80% 89% reduction) compared with PCA-only feature reduction and non-optimized baselines [7]. The results confirm that ABC-driven selection of discriminative features at the fusion layer offers an effective balance between accuracy, feature compactness, and computational efficiency in real-time biometric person authentication.},
        keywords = {Multimodal biometrics; multi-algorithm fusion; feature-level fusion; artificial bee colony; feature selection; wrapper method; fingerprint; iris; palmprint; person authentication; biometric recognition; swarm intelligence; optimization.},
        month = {December},
        }