GANs generate synthetic fingerphotos for biometric authentication research

Researchers have explored the generation of synthetic fingerphotos using advanced Generative Adversarial Networks (GANs), specifically StyleGAN2-ADA and StyleGAN3. This work aims to address the scarcity of contactless fingerprint data and the associated privacy risks by creating realistic synthetic images. The study evaluates the generated fingerphotos based on their realism, privacy preservation, and variety by comparing biometric feature statistics and match scores against real fingerphotos and among synthetic ones. AI

IMPACT Enables development and evaluation of contactless biometric systems without relying on sensitive real-world data.

RANK_REASON This is a research paper detailing a novel method for generating synthetic data using GANs for biometric authentication. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• arXiv
• StyleGAN2-ADA
• StyleGAN3
• Syed Konain Abbas

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →