Data Reliability Testing Framework for Biometric Datasets Using Synthetic Iris and Fingerprint Images Generated via Deep Generative Models

This paper presents a comprehensive data reliability testing framework for evaluating synthetic biometric data, addressing privacy concerns in fingerprint and iris recognition systems. This unified and modality-independent methodology establishes six quantitative metrics: randomness, quality similarity, attribute similarity, non-duplication, ID-preservation, and geometric diversity. The framework is implemented through a novel RD-Net architecture consisting of a Random Network for privacy protection and a Deterministic Network for maintaining essential biometric characteristics. Experiments using public datasets (FVC 2002, IITDelhi-Iris, and CASIA-Iris-V4) demonstrate that synthetic samples maintain high dissimilarity from source datasets while preserving their structural properties. The synthetic biometric data generated through the proposed Random Network and Deterministic Network architectures are evaluated using the data reliability testing framework, confirming distribution similarity with real data across all proposed metrics and achieving scores over 80. This approach offers a method for generating and evaluating synthetic biometric data that balances privacy protection with functional validity in biometric system development and testing.