Fusion of Hand Biometrics for Border Control Involving Fingerprint and Finger Vein

In this paper, we proposed an advanced multimodal fusion technique for fingerprint and finger vein recognition algorithms, incorporating novel improvements to established methods. Leveraging Scale-Invariant Feature Transform (SIFT) and Fast Library for Approximate Nearest Neighbors (FLANN), our approach integrates preprocessing enhancements such as Contrast Limited Adaptive Histogram Equalization (CLAHE) and a robust descriptor alignment mechanism to optimize feature extraction and matching. This innovation enhances security, robustness, accuracy, and privacy in biometric systems. Additionally, the fusion of fingerprint and finger vein modalities is implemented at both score-level and feature-level, where feature-level fusion demonstrates superior performance by effectively addressing compatibility issues between modalities and reducing information leakage. Extensive evaluations using databases such as SOCOFing, FVC, CASIA, FV-USM, PLUSVein-FV3, and UTFVP validate the effectiveness of the proposed system. Our results show that feature-level fusion outperforms traditional approaches, achieving higher accuracy and resilience against environmental factors. This study provides a scalable and practical solution for contemporary biometric verification needs, particularly in border control and security applications.