EDIL-SegRayDP: Training-Free Iris Segmentation via Segmentation-First Ray-Wise Dynamic Programming
DOI:
https://doi.org/10.4108/eetinis.132.12656Keywords:
Iris segmentation, Training-free, Dynamic programming, Occlusion modeling, Explainable biometricsAbstract
Iris segmentation remains a critical yet challenging stage in biometric recognition, especially under off- axis capture, eyelid and eyelash occlusion, specular reflections, and illumination variations that violate the circular and unobstructed assumptions of classical pipelines. We present EDIL-SegRayDP, a training-free and explainable iris segmentation framework that departs from the conventional localization-first paradigm by treating annulus recovery as the primary optimization objective. Rather than committing early to a global center/radius hypothesis and refining it afterward, the proposed method performs segmentation-first boundary recovery with segmentation-aware center rescue and fail-safe outer-boundary control. Occlusion is handled explicitly through geometry-normalized masking and validity-aware annulus construction, while all key parameters are defined in scale-normalized form for cross-dataset portability. Experiments under a fixed-configuration protocol on IITD and CASIA-IrisV4-Interval show strong non-CNN performance with CPU-only inference, achieving an iris-mask mean Dice of 0.9106 on IITD and 0.9377 on CASIA-IrisV4- Interval, with corresponding pupil Dice of 0.9763 and 0.9755. Additional full-benchmark evaluations on CASIA-IrisV4-Lamp and CASIA-IrisV4-Thousand further confirm the portability of the proposed framework across more challenging and larger-scale subsets. Under the evaluation protocol adopted in this study, these results compare favorably with a recent training-free reference, supporting EDIL-SegRayDP as a competitive and interpretable training-free alternative for iris segmentation under non-ideal imaging conditions.
Downloads
References
[1] Daugman J. How iris recognition works. IEEE Trans- actions on Circuits and Systems for Video Technology. 2004;14(1):21-30.
[2] Wildes RP. Iris recognition: an emerging biometric technology. Proceedings of the IEEE. 1997;85(9):1348- 63.
[3] Tan T, He Z, Sun Z. Efficient and robust segmentation of noisy iris images for non-cooperative iris recognition. Image and Vision Computing. 2010;28(2):223-30. 13 Trong-Thua Huynh et al.
[4] Ross A, Shah S. Segmenting Non-Ideal Irises Using Geodesic Active Contours. In: Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference; 2006. p. 1-6.
[5] Wang C, Muhammad J, Wang Y, He Z, Sun Z. Towards Complete and Accurate Iris Segmentation Using Deep Multi-Task Attention Network for Non-Cooperative Iris Recognition. IEEE Transactions on Information Forensics and Security. 2020;15:2944-59.
[6] Sharma G, Jaswal G, Nigam A, Ramachandra R. FISNET: A Learnable Fusion-Based Iris Segmentation Network Improving Robustness Across NIR and VIS Modalities. IEEE Access. 2025;13:101472-90.
[7] Daugman JG. High confidence visual recognition of persons by a test of statistical independence. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1993;15(11):1148-61.
[8] Masek L. Recognition of Human Iris Patterns for Biometric Identification [Master’s Thesis]. The University of Western Australia; 2003.
[9] Labati RD, Sansone C, Scotti F. Non-ideal iris segmentation using polar spline RANSAC and low-level energy minimization. Computer Vision and Image Understanding. 2020;201:102787.
[10] Gautam G, Mukhopadhyay S. An adaptive localization of pupil degraded by eyelash occlusion and poor contrast. Multimedia Tools and Applications. 2019;78(6):6655-77.
[11] Jan F, Min-Allah N, Agha S, Usman I, Khan I. A robust iris localization scheme for the iris recognition. Multimedia Tools and Applications. 2021;80(3):4579- 605.
[12] Mathias GP, Gagan JH, Mallya BV, Kumar JRH. A unified approach for automated segmentation of pupil and iris in on-axis images. Computer Methods and Programs in Biomedicine Update. 2022;2:100084.
[13] Sumi MR, Das P, Hossain A, Dey S, Schuckers S. A Comprehensive Evaluation of Iris Segmentation on Benchmarking Datasets. Sensors. 2024;24(21):7079.
[14] Xia C, Yan Y, Zhang R, Liu Y, Wang Q. A Light Spatial-Frequency Network for Robust Iris Segmentation and Localization. Applied Soft Computing. 2025;175:113009.
[15] Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Medical Image Computing and Computer-Assisted Intervention (MICCAI); 2015. p. 234-41.
[16] Lozej J, Meden B, Štruc V. End-to-End Iris Segmentation Using U-Net. In: IEEE International Work Conference on Bioinspired Intelligence (IWOBI); 2018. p. 1-8.
[17] Jha RR, Jaswal G, Gupta D, Saini S, Nigam A. PixISegNet: Pixel-level iris segmentation network using convolutional encoder–decoder with stacked hourglass bottleneck. IET Biometrics. 2020;9(1):11-24.
[18] Arsalan M, Kim DS, Lee MB, Owais M, Park KR. IrisDenseNet: Robust Iris Segmentation Using Densely Connected Fully Convolutional Networks in the Images by Visible Light and Near-Infrared Light Camera Sensors. Sensors. 2018;18(5):1501.
[19] Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, et al. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV); 2021. p. 10012-22.
[20] Cao H, Wang Y, Chen J, Jiang D, Zhang X, Tian Q, et al. Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation. In: Computer Vision – ECCV 2022 Workshops; 2022. p. 205-18.
[21] Kirillov A, Mintun E, Ravi N, Mao H, Rolland C, Gustafson L, et al. Segment Anything. arXiv preprint arXiv:230402643. 2023. Available from: https:// arxiv.org/abs/2304.02643.
[22] Farmanifard P, Ross A. Iris-SAM: Iris Segmentation Using a Foundation Model. In: International Conference on Pattern Recognition and Artificial Intelligence. Springer Nature Singapore; 2024. p. 394-409.
[23] Kumar JRH, Teotia K. Automatic Pupil Segmentation Based On Circular Active Discs. In: TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON); 2019. p. 1932-6.
[24] Sardar M, Banerjee S, Mitra S. Iris Segmentation Using Interactive Deep Learning. IEEE Access. 2020;8:219322- 30.
[25] Umer S, Dhara BC, Chanda B. Iris recognition using multiscale morphologic features. Pattern Recognition Letters. 2015;65:67-74.
[26] Al-Waisy AS, Qahwaji R, Ipson S, Al-Fahdawi S, Nagem TAM. A multi-biometric iris recognition system based on a deep learning approach. Pattern Analysis and Applications. 2018;21(3):783-802.
[27] Gangwar AK, Joshi A, Singh A, Alonso-Fernandez F, Bigun J. IrisSeg: A Fast and Robust Iris Segmentation Framework for Non-Ideal Iris Images. In: 2016 International Conference on Biometrics (ICB). Halmstad, Sweden; 2016. p. 1-8.
[28] Wu X, Zhao L. Study on Iris Segmentation Algorithm Based on Dense U-Net. IEEE Access. 2019;7:123959-68.
[29] Petrovska D, Mayoue A. Description and Documentation of the BioSecure Software Library. BioSecure; 2007
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2026 Trong-Thua Huynh, De-Thu Huynh, Cong-Sang Duong
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 3.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
