Research map / Image generation / GANs
FingerGAN: A Constrained Fingerprint Generation Scheme for Latent Fingerprint Enhancement
Yanming Zhu, Xuefei Yin, Jiankun Hu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add discriminator (embed SC-DAE in a GAN) (ablation) | FingerGAN · NIST SD27 (258 rolled reference) | rank-1 identification accuracy (%): 70.54% -> 76.36% | Improved |
| use skeleton map as ground truth instead of gray image (ablation) | FingerGAN · NIST SD27 (258 rolled reference) | rank-1 identification accuracy (%): 70.15% -> 76.36% | Improved |
| add Gaussian-based minutia weight map to reconstruction loss (ablation) | FingerGAN · NIST SD27 (258 rolled reference) | rank-1 identification accuracy (%): 62.02% -> 76.36% | Improved |
| use FingerGAN instead of Cao's method | FingerGAN · NIST SD27 (27,258 rolled reference) | rank-1 identification accuracy (%): 52.71% -> 59.69% | Improved |
| use FingerGAN instead of Cao's method | FingerGAN · IIIT-Delhi MOLF reference L | rank-1 identification accuracy (%): 26.47% -> 29.43% | Improved |
| use FingerGAN instead of Cao's method | FingerGAN · IIIT-Delhi MOLF reference C | rank-1 identification accuracy (%): 24.02% -> 25.34% | Improved |
| use FingerGAN instead of Cao's method | FingerGAN · IIIT-Delhi MOLF reference S | rank-1 identification accuracy (%): 21.47% -> 22.23% | Improved |
| use FingerGAN instead of Cao's method | FingerGAN · NIST SD27 minutia recovery | rank-1 identification accuracy (%): 1,887 -> 1,982 genuine minutiae; 12,235 -> 11,152 fake | Improved |
Closest papers by meaning
- PrintsGAN: Synthetic Fingerprint Generator (TPAMI 2022 · similarity 0.89)
- FingerprintNet: Synthesized Fingerprints for Generated Image Detection (ECCV 2022 · similarity 0.86)
- Automated Latent Fingerprint Recognition (TPAMI 2018 · similarity 0.86)
- Attributing Image Generative Models using Latent Fingerprints (ICML 2023 · similarity 0.86)
- Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints (ICCV 2019 · similarity 0.86)
- OmniMark: Efficient and Scalable Latent Diffusion Model Fingerprinting (AAAI 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
