Lowering the Barrier to IREX Participation: Open-Source Algorithms, Toolkit, and Benchmarking for Iris Recognition

2026-05-20

AI Summary

This work addresses the lack of support for the IREX evaluation protocol in existing open-source iris recognition systems, which has hindered community participation. The authors propose two deep learning–based open-source algorithms, TripletIris and ArcIris, integrating iris segmentation and circle-fitting modules, and provide the first IREX-compliant reference implementations in both C++ and Python, along with submission templates. Key technical components include triplet loss with Batch-Hard mining, ArcFace loss, and human-eye saliency–driven filtering (HDBIF). The methods are validated across eight mainstream datasets and pass official IREX-X evaluations for all components except CRYPTS, which is excluded due to temporal constraints. By releasing fully open-source code, pre-trained models, and a complete toolchain, this project substantially lowers the barrier to IREX participation.

Abstract

This paper proposes two new open-source iris recognition algorithms, providing both Python and IREX-compliant C++ implementations to be submitted to the official IREX X program. This work has two primary goals: (a) to conduct the first-ever assessment of open-source iris recognition solutions according to IREX testing protocols, and (b) to offer a model C++ submission that significantly facilitates the entry of other teams' open-source methods into the IREX evaluation. The new methods consist of two Neural Networks trained with: (i) Triplet loss with Batch-Hard Triplet mining (TripletIris), and (ii) ArcFace loss (ArcIris). The paper also provides open-source IREX-compliant C++ implementations of two existing methods: (a) an iris image filtering-based algorithm utilizing human saliency-driven kernels (HDBIF), and (b) a human-interpretable algorithm for detecting and comparing Fuchs' crypts (CRYPTS). Except for CRYPTS, which faced timing constraints during 1:N search, these methods have undergone the official IREX X evaluation and have also been assessed using several popular academic benchmarks: Quality-Face/Iris Research Ensemble, Warsaw-Biobase Post-Mortem Iris, CASIA-Iris-Thousand-V4, CASIA-Iris-Lamp-V4, IIT Delhi Iris Database, IIITD Contact Lens Iris Database, NDIris3D, and Notre Dame Variable Iris Image Quality Release 2. Finally, this paper also provides open-source models for iris segmentation and circle estimation that can be incorporated into any new iris recognition method.

Problem

• IREX
• iris recognition
• open-source
• benchmarking
• algorithm submission

Innovation

• open-source iris recognition
• IREX benchmarking
• TripletIris
• ArcIris
• iris segmentation