Decision Support System for the Selection of Thumbprint Recognition Algorithms in Biometric Security Systems

Abstract

This study investigates fingerprint recognition in immigration operations, emphasizing the role of biometric verification in enhancing security, fairness, and operational efficiency in international mobility. To address the uncertainty, vagueness, and imprecision inherent in fingerprint identification, a novel decision-making framework is proposed by integrating interval-valued picture fuzzy (IVPF) information. Fairly aggregation operators are introduced to combine decision makers' evaluations, while extracted fingerprint features are modeled using positive, neutral, and negative membership degrees within the IVPF environment. Objective criterion weights are determined using the criteria importance through intercriteria correlation (CRITIC) method, and individual ranking is performed via the alternative ranking order method with two-step normalisation (AROMAN). Furthermore, a comparative analysis is conducted by employing linear regression, decision tree, extra tree, and random forest models to rank alternatives and assess algorithmic performance. The results demonstrate that hybrid approaches outperform standalone machine learning models by effectively balancing accuracy, adaptability, and robustness. Overall, the proposed CRITIC–AROMAN–IVPF framework provides a transparent, data-driven methodology for algorithm evaluation and alternative ranking, offering valuable insights for biometric system design and decision-support applications.