Research map / Label-efficient and robust learning / Recognition and long-tail
Automated Latent Fingerprint Recognition
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 texture template to the two minutiae templates (ablation) | Proposed system · NIST SD27 | rank-1 identification accuracy (%): 58.5 -> 64.7 | Improved |
| add texture template to the two minutiae templates (ablation) | Proposed system · WVU latent DB | rank-1 identification accuracy (%): 70.6 -> 75.3 | Improved |
| use ConvNet-learned minutiae descriptor instead of MCC (ablation) | Minutiae template 1 · NIST SD27 | rank-1 identification accuracy (%): 21.3 -> 51.2 | Improved |
| use ConvNet-learned minutiae descriptor instead of MCC (ablation) | Minutiae template 1 · WVU latent DB | rank-1 identification accuracy (%): 35.2 -> 65.7 | Improved |
| use 3 of 14 patch ConvNets instead of all 14 (ablation) | Minutiae descriptor · NIST SD27 | rank-1 identification accuracy (%): 75.6 -> 74.4 | No clear effect |
| fuse COTS latent AFIS with proposed system (score-level) | Proposed system · NIST SD27 | rank-1 identification accuracy (%): 66.7 -> 73.3 | Improved |
| fuse COTS latent AFIS with proposed system (rank-level) | Proposed system · WVU latent DB | rank-1 identification accuracy (%): 75.3 -> 78.4 | Improved |
| fuse any two templates versus a single template (ablation) | Proposed system · NIST SD27 and WVU | rank-1 identification accuracy (%) | Improved |
| use ConvNet ridge flow (template 1) instead of dictionary ridge flow (template 2) (ablation) | Minutiae templates · NIST SD27 and WVU | rank-1 identification accuracy (%) | Improved |
Closest papers by meaning
- FingerGAN: A Constrained Fingerprint Generation Scheme for Latent Fingerprint Enhancement (TPAMI 2023 · similarity 0.86)
- Learning a Fixed-Length Fingerprint Representation (TPAMI 2019 · similarity 0.83)
- OmniMark: Efficient and Scalable Latent Diffusion Model Fingerprinting (AAAI 2025 · similarity 0.81)
- Intersecting-Boundary-Sensitive Fingerprinting for Tampering Detection of DNN Models (ICML 2024 · similarity 0.80)
- Blind-Touch: Homomorphic Encryption-Based Distributed Neural Network Inference for Privacy-Preserving Fingerprint Authentication (AAAI 2024 · similarity 0.79)
- Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image Detection (NeurIPS 2025 · similarity 0.79)
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.
