New AI model detects clear contact lenses to improve iris recognition

Researchers have developed a novel two-stage framework to detect clear contact lenses, which can impact iris recognition accuracy. The system first identifies patterned lenses using existing methods and then employs a ConvNeXt-Base model with Mask-Guided Spatial Attention to distinguish between clear lenses and no lenses. This approach, incorporating anatomical masks and attention mechanisms, achieves high accuracy across multiple datasets and can improve iris verification performance when integrated with score calibration. AI

IMPACT This research could lead to more robust biometric security systems by mitigating the impact of clear contact lenses on iris recognition.

RANK_REASON This is a research paper detailing a novel technical approach to a specific problem. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• ConvNeXt-Base
• Hough
• Mask-Guided Spatial Attention
• Parisa Farmanifard
• Squeeze-and-Excitation Networks
• VeriEye

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →