![[2510.06170] Smartphone-based iris recognition through high-quality visible-spectrum iris image capture.V2](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2510.06170] Smartphone-based iris recognition through high-quality visible-spectrum iris image capture.V2
Summary
This paper presents a smartphone-based iris recognition system using visible-spectrum imaging, demonstrating high accuracy through a custom application and a new dataset.
Why It Matters
The research addresses challenges in iris recognition on smartphones, such as illumination variability and image quality. By establishing a standardized capture process and introducing efficient models, it opens pathways for practical biometric applications in mobile devices, enhancing security and user convenience.
Key Takeaways
- Introduces a compact pipeline for iris recognition compliant with ISO/IEC standards.
- Demonstrates high accuracy with a true acceptance rate of 97.9% at a low false acceptance rate.
- Releases a new dataset (CUVIRIS) to support reproducibility in iris recognition research.
- Utilizes a lightweight MobileNetV3-based model for efficient processing on smartphones.
- Confirms that standardized capture methods can significantly improve iris recognition accuracy.
Electrical Engineering and Systems Science > Image and Video Processing arXiv:2510.06170 (eess) This paper has been withdrawn by Naveenkumar Venkataswamy Mr [Submitted on 7 Oct 2025 (v1), last revised 20 Feb 2026 (this version, v3)] Title:Smartphone-based iris recognition through high-quality visible-spectrum iris image capture.V2 Authors:Naveenkumar G Venkataswamy, Yu Liu, Soumyabrata Dey, Stephanie Schuckers, Masudul H Imtiaz View a PDF of the paper titled Smartphone-based iris recognition through high-quality visible-spectrum iris image capture.V2, by Naveenkumar G Venkataswamy and 4 other authors No PDF available, click to view other formats 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 prio...