Research map / Label-efficient and robust learning / Recognition and long-tail
Learning a Fixed-Length Fingerprint Representation
Joshua J. Engelsma, Kai Cao, Anil K. Jain
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 automatic alignment module (ablation) | DeepPrint · FVC 2004 DB1 A authentication | TAR @ FAR=0.1%: 72.86% -> 88.0% | Improved |
| add minutiae domain knowledge on top of alignment (ablation) | DeepPrint · FVC 2004 DB1 A authentication | TAR @ FAR=0.1%: 88.0% -> 97.5% | Improved |
| add alignment module (ablation) | DeepPrint · NIST SD4 | TAR @ FAR=0.1%: 96.95% -> 96.65% | No clear effect |
| add alignment module (ablation) | DeepPrint · NIST SD14 | TAR @ FAR=0.1%: 97.96% -> 96.52% | Hurt |
| add minutiae domain knowledge on top of alignment (ablation) | DeepPrint · NIST SD4 | TAR @ FAR=0.1%: 96.65% -> 97.9% | Improved |
| add minutiae domain knowledge on top of alignment (ablation) | DeepPrint · NIST SD14 | TAR @ FAR=0.1%: 96.52% -> 98.55% | Improved |
| fuse minutiae and texture representations (ablation) | DeepPrint · FVC 2004 DB1 A authentication | TAR @ FAR=0.1%: 97.4% -> 97.5% | Improved |
| fuse minutiae and texture representations (ablation) | DeepPrint · NIST SD4 | TAR @ FAR=0.01%: 97.15% -> 97.9% | Improved |
| fuse minutiae and texture representations (ablation) | DeepPrint · NIST SD14 | TAR @ FAR=0.01%: 98.14% -> 98.55% | Improved |
| compress template from 768 to 200 bytes | DeepPrint · NIST SD4 | TAR @ FAR=0.01%: 97.95% -> 97.90% | No clear effect |
| sum score fusion with COTS A | DeepPrint · FVC 2004 DB1 A authentication | TAR @ FAR=0.1%: 97.5% -> 98.93% | Improved |
| fully homomorphic encryption matching | DeepPrint · NIST SD4 | TAR @ FAR=0.01%: 97.9% -> 96.9% | Hurt |
Closest papers by meaning
- Blind-Touch: Homomorphic Encryption-Based Distributed Neural Network Inference for Privacy-Preserving Fingerprint Authentication (AAAI 2024 · similarity 0.86)
- SDBF: Steep-Decision-Boundary Fingerprinting for Hard-Label Tampering Detection of DNN Models (CVPR 2025 · similarity 0.83)
- Scalable Fingerprinting of Large Language Models (NeurIPS 2025 · similarity 0.83)
- OmniMark: Efficient and Scalable Latent Diffusion Model Fingerprinting (AAAI 2025 · similarity 0.83)
- Intersecting-Boundary-Sensitive Fingerprinting for Tampering Detection of DNN Models (ICML 2024 · similarity 0.83)
- SIF: Semantically In-Distribution Fingerprints for Large Vision-Language Models (CVPR 2026 · 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.
