.png){kind=icon}
.png){kind=icon}
Return
ExplainablePR: Periocular recognition with interpretability in sight
.png){kind=icon}
OA
AI
J
V
B
H
DOI：10.1016/j.imavis.2026.106070.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Proposal of a framework that integrates biometric recognition with visual interpretations of the features that contribute the most to a match/non-match decision. • Use of adversarial generative models to create a synthetic set composed exclusively of “genuine” image pairs, accounting for cross domain robustness. • Comparisons against three classical image interpretability techniques (SHAP, LIME and saliency maps) and other state-of-the-art fine-grained visual recognisers, which demonstrate the proposed solution’s ability to deliver highly intuitive explanations, while maintaining effective recognition performance.
Keywords:
Periocular recognition
Biometrics
Explainability
Interpretability
Machine learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.2
Papers:
4.0K
Citations:
6.7K
Organization
Cited Papers