Detecting Clear Contact Lenses for Iris Recognition: A Two-Stage Mask-Guided Attention Approach

2026-08-09

AI Summary

This study addresses the often-overlooked impact of transparent contact lenses on iris recognition, which, despite their lack of visible texture, subtly degrade iris matching scores and increase verification error rates. The work presents the first systematic evaluation of this effect and introduces a two-stage detection and calibration framework. The first stage filters out cosmetic lenses, while the second leverages a ConvNeXt-Base architecture enhanced with anatomical region masks derived from Hough transforms and a novel Mask-Guided Spatial Attention module to focus on subtle limbal cues for distinguishing transparent lenses from bare eyes. Integrated Squeeze-and-Excitation recalibration and z-score-based matching score calibration further refine performance. Evaluated across four datasets, the method achieves contact lens detection accuracy of 90.0%–98.8% and reduces equal error rates (EER) by 4.1%–28.3% after calibration, significantly enhancing iris recognition robustness.

Abstract

This work focuses on the impact and detection of clear contact lenses in the context of iris recognition. While the detection of cosmetic or patterned contact lenses has been extensively studied under the presentation attack detection (PAD) paradigm, clear prescription contact lenses, that are typically transparent, have received comparatively less attention despite their widespread use. Unlike patterned lenses, clear lenses introduce no salient texture artifact, making them difficult to detect and are often assumed to have no impact on iris recognition. We first examine this assumption using the commercial VeriEye matcher on four benchmark datasets and show that clear lenses marginally degrade genuine match scores and increase verification error. We then propose a two-stage contact-lens detection framework. Stage~1 uses an existing PAD model to identify patterned lenses, while Stage~2 focuses on the more challenging clear-lens versus no-lens distinction using a ConvNeXt-Base model equipped with Mask-Guided Spatial Attention (MGSA). The proposed MGSA module incorporates a Hough-derived anatomical ROI mask together with learned spatial attention and Squeeze-and-Excitation channel recalibration, allowing the network to focus on subtle limbal cues associated with clear lens wear. Across four datasets, the full pipeline consisting of both patterned and clear contact lens detection achieves between 90.0\%--98.8\% accuracy. Finally, we introduce a z-score calibration method that adjusts VeriEye match scores when a clear lens is detected in the input images. This calibration reduces EER by 4.1\%--28.3\% across datasets, demonstrating that reliable clear contact lens detection can directly improve iris verification performance.

Problem

• clear contact lenses
• iris recognition
• presentation attack detection
• biometric verification
• limbal cues

Innovation

• Mask-Guided Spatial Attention
• Clear Contact Lens Detection
• Iris Recognition
• Presentation Attack Detection
• Score Calibration