Research map / Detection and segmentation / Open-set and few-shot detection
IRINA: Iris Recognition (Even) in Inaccurately Segmented Data
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use IRINA instead of Yang et al. | Iris recognition · CASIA-IrisV3-Lamp | AUC: 0.995 ± 4e−4 -> 0.999 ± 1e−4 | Helped |
| Use IRINA instead of Yang et al. | Iris recognition · CASIA-IrisV4-Lamp | AUC: 0.993 ± 5e−4 -> 0.995 ± 0.002 | Helped |
| Use IRINA instead of Yang et al. | Iris recognition · CASIA-IrisV4-Thousand | AUC: 0.988 ± 6e−4 -> 0.996 ± 0.001 | Helped |
| Use IRINA instead of Yang et al. | Iris recognition · WVU | AUC: 0.980 ± 0.001 -> 0.991 ± 0.002 | Helped |
| Use IRINA instead of Yang et al. | Iris recognition · CASIA-IrisV3-Lamp | EER: 0.021 ± 0.004 -> 0.006 ± 0.001 | Helped |
| Use IRINA instead of Yang et al. | Iris recognition · CASIA-IrisV4-Lamp | EER: 0.028 ± 0.004 -> 0.026 ± 0.005 | Helped |
| Use IRINA instead of Yang et al. | Iris recognition · CASIA-IrisV4-Thousand | EER: 0.045 ± 0.004 -> 0.030 ± 0.005 | Helped |
| Use IRINA instead of Yang et al. | Iris recognition · WVU | EER: 0.065 ± 0.008 -> 0.042 ± 0.008 | Helped |
| Use IRINA rather than Yang et al. and Sun and Tan under segmentation errors | Iris recognition · CASIA-IrisV4-Thousand with inaccurate segmentation | AUC | Helped |
| Use IRINA rather than Belcher and Du under segmentation errors | Iris recognition · CASIA-IrisV4-Thousand with inaccurate segmentation | AUC | Helped |
| Set α below 0.9, reducing local deformation-field variation (ablation) | IRINA · CASIA-IrisV3-Lamp | AUC | Hurt |
Closest papers by meaning
- ImmerIris: A Large-Scale Dataset and Benchmark for Off-Axis and Unconstrained Iris Recognition in Immersive Applications (CVPR 2026 · similarity 0.80)
- Show and Segment: Universal Medical Image Segmentation via In-Context Learning (CVPR 2025 · similarity 0.79)
- Kandinsky Conformal Prediction: Efficient Calibration of Image Segmentation Algorithms (CVPR 2024 · similarity 0.77)
- Makeup Prior Models for 3D Facial Makeup Estimation and Applications (CVPR 2024 · similarity 0.76)
- Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification (CVPR 2024 · similarity 0.76)
- ID-Patch: Robust ID Association for Group Photo Personalization (CVPR 2025 · similarity 0.75)
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.