Smartphone-based iris recognition through high-quality visible-spectrum iris image capture.V2

2025-10-07

AI Summary

To address performance degradation in smartphone-based visible-light iris recognition caused by large illumination variations, significant iris pigment heterogeneity, and nonstandardized acquisition, this paper proposes an end-to-end lightweight solution. We design an ISO-compliant standardized acquisition protocol and introduce CUVIRIS—the first publicly available dataset specifically curated for mobile visible-light iris recognition. We further pioneer the application of Transformer architectures to visible-light iris matching, proposing IrisFormer. Additionally, we develop a real-time Android acquisition system and LightIrisNet, a lightweight multi-task segmentation network. Evaluated at FAR = 0.01, our method achieves a TAR of 97.9% and an EER of 0.057%, significantly outperforming state-of-the-art approaches. These results demonstrate the feasibility of high-accuracy, high-robustness visible-light iris recognition on smartphones.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Smartphone-based iris recognition in the visible spectrum (VIS) remains difficult due to illumination variability, pigmentation differences, and the absence of standardized capture controls. This work presents a compact end-to-end pipeline that enforces ISO/IEC 29794-6 quality compliance at acquisition and demonstrates that accurate VIS iris recognition is feasible on commodity devices. Using a custom Android application performing real-time framing, sharpness evaluation, and feedback, we introduce the CUVIRIS dataset of 752 compliant images from 47 subjects. A lightweight MobileNetV3-based multi-task segmentation network (LightIrisNet) is developed for efficient on-device processing, and a transformer matcher (IrisFormer) is adapted to the VIS domain. Under a standardized protocol and comparative benchmarking against prior CNN baselines, OSIRIS attains a TAR of 97.9% at FAR=0.01 (EER=0.76%), while IrisFormer, trained only on UBIRIS.v2, achieves an EER of 0.057% on CUVIRIS. The acquisition app, trained models, and a public subset of the dataset are released to support reproducibility. These results confirm that standardized capture and VIS-adapted lightweight models enable accurate and practical iris recognition on smartphones.

Problem

• Addresses visible-spectrum iris recognition challenges on smartphones
• Develops lightweight models for efficient on-device iris processing
• Ensures ISO quality compliance through standardized capture controls

Innovation

• Android app enforces ISO quality compliance during capture
• LightIrisNet provides efficient on-device iris segmentation
• IrisFormer transformer adapts matching to visible spectrum