Conditional Synthetic Live and Spoof Fingerprint Generation

2025-10-19

AI Summary

To address the high privacy risks, substantial costs, and limited accessibility associated with acquiring real fingerprint data in fingerprint liveness detection research, this paper proposes a conditionally controllable, high-fidelity synthetic fingerprint generation framework. Methodologically, it introduces the first integration of StyleGAN2-ADA/3—trained to synthesize live fingerprints—with CycleGAN for cross-material domain translation, enabling identity-accurate paired generation of live and spoof fingerprints across diverse materials (e.g., silicone, gelatin). The resulting synthetic datasets, DB2 and DB3, each contain 1,500 identity-matched image pairs, achieving a Fréchet Inception Distance (FID) of 5.0. On liveness classification, the framework attains a true acceptance rate (TAR) of 99.47% at a false acceptance rate (FAR) of 0.01%. Quality assessment via NFIQ2 and MINDTCT confirms high fidelity and reliability, with no discernible identity leakage—demonstrating both strong privacy preservation and photorealistic synthesis capability.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Privacy

Application Category

• Security and Privacy: Data transparency and provenance
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Large fingerprint datasets, while important for training and evaluation, are time-consuming and expensive to collect and require strict privacy measures. Researchers are exploring the use of synthetic fingerprint data to address these issues. This paper presents a novel approach for generating synthetic fingerprint images (both spoof and live), addressing concerns related to privacy, cost, and accessibility in biometric data collection. Our approach utilizes conditional StyleGAN2-ADA and StyleGAN3 architectures to produce high-resolution synthetic live fingerprints, conditioned on specific finger identities (thumb through little finger). Additionally, we employ CycleGANs to translate these into realistic spoof fingerprints, simulating a variety of presentation attack materials (e.g., EcoFlex, Play-Doh). These synthetic spoof fingerprints are crucial for developing robust spoof detection systems. Through these generative models, we created two synthetic datasets (DB2 and DB3), each containing 1,500 fingerprint images of all ten fingers with multiple impressions per finger, and including corresponding spoofs in eight material types. The results indicate robust performance: our StyleGAN3 model achieves a Fréchet Inception Distance (FID) as low as 5, and the generated fingerprints achieve a True Accept Rate of 99.47% at a 0.01% False Accept Rate. The StyleGAN2-ADA model achieved a TAR of 98.67% at the same 0.01% FAR. We assess fingerprint quality using standard metrics (NFIQ2, MINDTCT), and notably, matching experiments confirm strong privacy preservation, with no significant evidence of identity leakage, confirming the strong privacy-preserving properties of our synthetic datasets.

Problem

• Generating synthetic live and spoof fingerprints to address privacy concerns
• Creating realistic fingerprint datasets to reduce collection costs and time
• Developing robust spoof detection systems using synthetic presentation attacks

Innovation

• Conditional GANs generate high-resolution synthetic live fingerprints
• CycleGANs translate live prints into realistic spoof fingerprints
• Generated datasets ensure privacy with no identity leakage evidence