Skip to main content
SpringerLink
Log in

Analysis of V-Net Architecture for Iris Segmentation in Unconstrained Scenarios

  • Original Research
  • Published:
SN Computer Science Aims and scope Submit manuscript

Abstract

Iris segmentation contains the most significant character in the iris recognition system. An accurate iris segmentation helps to increase the accuracy of iris recognition in any biometric system. However, the robustness and efficiency of conventional iris segmentation methodologies are facing massive challenges in a non-cooperative environment because of unfavorable factors, for instance, blur, occlusion, off-axis, low resolution, motion, and specular reflections. These factors severely affect the accuracy of the iris segmentation approaches. In this article, a novel Iris segmentation approach has been obtained with V-Net architectures to accurately localize the boundaries of the iris image with semantic segmentation mask synthesis. A novel image processing technique: YCrCb and HSV color space, has also been utilized to select saliency point set and recover the iris boundary. A detailed analytical study has been obtained with the U-Net and its modified architecture to understand the drawbacks of the U-Net architectures and how V-Net can overcome them. Experimental Results consolidate that the iris segmentation with V-Net achieves 95.6% mean IOU value, whereas U-Net can only achieve 92.3%. So V-Net can easily outperform the existing state-of-the-art approaches on the challenging UBIRIS database.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Availability of Data and Materials

This experiment uses the UBIRIS dataset, which is publicly available for iris segmentation.

Code Availability

All the codes are now kept privately in a GitHub repository, The link will be provided after acceptance of the report, and the repository will be publicly available from that time.

References

  1. Abomhara M, Yayilgan SY, Nweke LO, Székely Z. A comparison of primary stakeholders’ views on the deployment of biometric technologies in border man- agement: case study of SMart mobILity at the European land borders. Technol Soc. 2021;64:101484.

    Article  Google Scholar 

  2. Esteva A, Chou K, Yeung S, Naik N, Madani A, Mottaghi A, Liu Y, Topol E, Dean J, Socher R. Deep learning-enabled medical computer vision. NPJ Digit Med. 2021;4(1):1–9.

    Article  Google Scholar 

  3. Zhang Y, Sun X, Dong J, Chen C, Lv Q. GPNet: gated pyramid network for semantic segmentation. Pattern Recogn. 2021;115:107940.

    Article  Google Scholar 

  4. Shankar TN, Rakesh P, Rao TB, Bharadwaj LH, Rakesh C, Madhuri ML. Providing security to land record with the computation of iris, blockchain, and one time password. In: 2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS). IEEE, 2021; pp. 226–231.

  5. Dronky MR, Khalifa W, Roushdy M. Using residual images with BSIF for iris liveness detection. Expert Syst Appl. 2021;182:115266.

    Article  Google Scholar 

  6. Li Y, Hall NE, Pershing S, Hyman L, Haller JA, Lee AY, Lee CS, Chiang M, Lum F, Miller JW, Lorch A. Age, gender, and laterality of retinal vascular occlusion: a retrospective study from the IRIS® Registry. Ophthalmol Retin. 2021;6:161–71.

    Article  Google Scholar 

  7. Jayanthi J, Lydia EL, Krishnaraj N, Jayasankar T, Babu RL, Suji RA. An effective deep learning features based integrated framework for iris detection and recognition. J Ambient Intell Humaniz Comput. 2021;12:3271–81.

    Article  Google Scholar 

  8. Massey ZB, Brockenberry LO, Harrell PT. Vaping, smartphones, and social media use among young adults: snapchat is the platform of choice for young adult vapers. Addict Behav. 2021;112:106576.

    Article  Google Scholar 

  9. Zhang Y. Backtracking search algorithm with specular reflection learning for global optimization. Knowl Based Syst. 2021;212:106546.

    Article  Google Scholar 

  10. Yu S, Lakshminarayanan V. Fractal dimension and retinal pathology: a meta-analysis. Appl Sci. 2021;11(5):2376.

    Article  Google Scholar 

  11. Nazmdeh V, Mortazavi S, Tajeddin D, Nazmdeh H, Asem MM. Iris recognition; from classic to modern approaches. In: 2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC). IEEE, 2019; pp 0981–0988.

  12. Jagadeesh N, Patil CM. Software implementation procedure of the development of an iris-biometric identification system using image processing techniques. In: 2017 International Conference on Computing Methodologies and Communication (IC-CMC). IEEE, 2017; pp 673–683.

  13. Chen Y, Wu C, Wang Y. Whether normalized or not? Towards more robust iris recognition using dynamic programming. Image Vis Comput. 2021;107:104112.

    Article  Google Scholar 

  14. Udayakumar E, Ramesh C, Yogeshwaran K, Tamilselvan S, Srihari K. An enhanced face and iris recognition-based new generation security system. In: Proceedings of First International Conference on Computing, Communications, and Cyber-Security (IC4S 2019). Springer, Singapore, 2020; pp 845–855.

  15. Hussein NJ. Robust iris recognition framework using computer vision algorithms. In: 2020 4th International Conference on Smart Grid and Smart Cities (ICSGSC). IEEE, 2020; pp. 101–108.

  16. Proença H, Alexandre LA. Toward non-cooperative iris recognition: a classification approach using multiple signatures. IEEE Trans Pattern Anal Mach Intell. 2007;29(4):607–12.

    Article  Google Scholar 

  17. Devi K, Gupta P, Grover D, Dhindsa A. An effective texture feature extraction approach for iris recognition system. In: 2016 2nd International Conference on Advances in Computing, Communication, and Automation (ICACCA) (Fall). IEEE, 2016; pp 1–5.

  18. Jagadeesh N, Patil CM. Conceptual view of the Iris recognition systems in the biometric world using image processing techniques. In: 2017 International Conference on Computing Methodologies and Communication (ICCMC). IEEE, 2017; pp 1018–1022.

  19. Nigam I, Vatsa M, Singh R. Ocular biometrics: a survey of modalities and fusion approaches. Inform Fus. 2015;26:1–35.

    Article  Google Scholar 

  20. He Z, Tan T, Sun Z, Qiu X. Toward accurate and fast iris segmentation for iris biometrics. IEEE Trans Pattern Anal Mach Intell. 2008;31(9):1670–84.

    Google Scholar 

  21. Bazrafkan S, Thavalengal S, Corcoran P. An end to end deep neural network for iris segmentation in unconstrained scenarios. Neural Netw. 2018;106:79–95.

    Article  Google Scholar 

  22. Lian S, Luo Z, Zhong Z, Lin X, Su S, Li S. Attention guided U-Net for accurate iris segmentation. J Vis Commun Image Represent. 2018;56:296–304.

    Article  Google Scholar 

  23. Arsalan M, Kim DS, Lee MB, Owais M, Park KR. FRED-Net: fully residual encoder–decoder network for accurate iris segmentation. Expert Syst Appl. 2019;122:217–41.

    Article  Google Scholar 

  24. Hofbauer H, Jalilian E, Uhl A. Exploiting superior CNN-based iris seg- mentation for better recognition accuracy. Pattern Recogn Lett. 2019;120:17–23.

    Article  Google Scholar 

  25. Lozej J, Meden B, Struc V, Peer P. End-to-end iris segmentation using u-net. In: 2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI). IEEE 2018; pp. 1–6.

  26. Jalilian E, Uhl A. Iris segmentation using fully convolutional encoder–decoder networks. In: Deep learning for biometrics. Cham: Springer; 2017. p. 133–55.

    Chapter  Google Scholar 

  27. Okokpujie K, Noma-Osaghae E, John S, Ajulibe A. An improved iris segmentation technique using circular Hough transform. In: IT convergence and security 2017. Singapore: Springer; 2018. p. 203–11.

    Chapter  Google Scholar 

  28. Jalilian E, Uhl A, Kwitt R. Domain adaptation for CNN based iris segmentation. In: 2017 International Conference of the Biometrics Special Interest Group (BIOSIG). IEEE 2017; pp. 1–6.

  29. 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 Trans Inf Forensics Secur. 2020;15:2944–59.

    Article  Google Scholar 

  30. Varkarakis V, Bazrafkan S, Corcoran P. Deep neural network and data augmentation methodology for off-axis iris segmentation in wearable headsets. Neural Netw. 2020;121:101–21.

    Article  Google Scholar 

  31. 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 Biom. 2020;9(1):11–24.

    Article  Google Scholar 

  32. Bezerra CS, Laroca R, Lucio DR, Severo E, Oliveira LF, Britto AS, Menotti D. Robust iris segmentation based on fully convolutional net- works and generative adversarial networks. In: 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI). IEEE 2018; pp. 281–288.

  33. Jan F, Min-Allah N. An effective iris segmentation scheme for noisy images. Biocybern Biomed Eng. 2020;40(3):1064–80.

    Article  Google Scholar 

  34. Lakra A, Tripathi P, Keshari R, Vatsa M, Singh R. Segdensenet: Iris segmentation for pre-and-post cataract surgery. In: 2018 24th International Conference on Pattern Recognition (ICPR). IEEE 2018; pp. 3150–3155.

  35. Zhang W, Lu X, Gu Y, Liu Y, Meng X, Li J. A robust iris segmentation scheme based on improved U-net. IEEE Access. 2019;7:85082–9.

    Article  Google Scholar 

  36. Ahmad S, Fuller B. Unconstrained iris segmentation using convolutional neural networks. In: Asian Conference on Computer Vision. Springer, Cham 2018; pp. 450–466.

  37. Labati RD, Muñoz E, Piuri V, Ross A, Scotti F. Nonideal iris seg- mentation using Polar Spline RANSAC and illumination compensation. Comput Vis Image Underst. 2019;188:102787.

    Article  Google Scholar 

  38. Chen Y, Wang W, Zeng Z, Wang Y. An adaptive CNNs technology for robust iris segmentation. IEEE Access. 2019;7:64517–32.

    Article  Google Scholar 

  39. Ouabida E, Essadique A, Bouzid A. Vander Lugt correlator based active contours for iris segmentation and tracking. Expert Syst Appl. 2017;71:383–95.

    Article  Google Scholar 

  40. Rapaka S, Kumar PR. Efficient approach for nonideal iris segmentation using improved particle swarm optimisation-based multilevel thresholding and geodesic active contours. IET Image Proc. 2018;12(10):1721–9.

    Article  Google Scholar 

  41. Yang Y, Shen P, Chen C. A robust iris segmentation using fully convolutional network with dilated convolutions. In: 2018 IEEE International Symposium on Multimedia (ISM). IEEE 2018; pp. 9–16.

  42. Fuentes-Hurtado F, Naranjo V, Diego-Mas JA, Alcañiz M. A hybrid method for accurate iris segmentation on at-a-distance visible-wavelength images. EURASIP J Image Video Process. 2019;2019(1):1–14.

    Article  Google Scholar 

  43. Shang Q, Zhao Y, Chen Z, Hao H, Li F, Zhang X, Liu J. Automated iris segmentation from anterior segment oct images with occludable angles via local phase tensor. In: 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE 2019; pp. 4745–4749.

  44. Pattar SY. An efficient framework for iris segmentation with additional pressure term in the active contour model and classification. In: 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS). IEEE 2021; pp. 680–685.

  45. Wang C, He Y, Liu Y, He Z, He R, Sun Z. ScleraSegNet: an improved u-net model with attention for accurate sclera segmentation. In 2019 International Conference on Biometrics (ICB). IEEE 2019; pp. 1–8.

  46. Jan F, Alrashed S, Min-Allah N. Iris segmentation for nonideal Iris biometric systems. Multimed Tools Appl 2021; pp.1–29.

  47. Chowdhury T, Shivakumara P, Pal U, Lu T, Raghavendra R, Chanda S. DCINN: deformable convolution and inception based neural network for tattoo text detection through skin region. In: International Conference on Document Analysis and Recognition. Springer, Cham, 2021; pp. 335–350.

  48. Kang C, Wu C, Fan J. Entropy-based circular histogram thresholding for color image segmentation. SIViP. 2021;15(1):129–38.

    Article  Google Scholar 

  49. Tan W, Liu P, Li X, Liu Y, Zhou Q, Chen C, Gong Z, Yin X, Zhang Y. Classification of COVID-19 pneumonia from chest CT images based on reconstructed super-resolution images and VGG neural network. Health Inform Sci Syst. 2021;9(1):1–12.

    Article  Google Scholar 

  50. Proença H, Filipe S, Santos R, Oliveira J, Alexandre LA. The UBIRIS v2: a database of visible wavelength iris images captured on-the-move and at-a-distance. IEEE Trans Pattern Anal Mach Intell. 2009;32(8):1529–35.

    Article  Google Scholar 

  51. Emeršič Ž, Gabriel LL, Štruc V, Peer P. Convolutional encoder–decoder networks for pixel-wise ear detection and segmentation. IET Biom. 2018;7(3):175–84.

    Article  Google Scholar 

  52. Basiri ME, Nemati S, Abdar M, Cambria E, Acharya UR. ABCDM: An attention-based bidirectional CNN-RNN deep model for sentiment analysis. Futur Gener Comput Syst. 2021;115:279–94.

    Article  Google Scholar 

  53. Zhu H, Ma M, Ma W, Jiao L, Hong S, Shen J, Hou B. A spatial-channel progressive fusion ResNet for remote sensing classification. Inform Fus. 2021;70:72–87.

    Article  Google Scholar 

  54. Riasatian A, Babaie M, Maleki D, Kalra S, Valipour M, Hemati S, Zaveri M, Safarpoor A, Shafiei S, Afshari M, Rasoolijaberi M. Fine-tuning and train- ing of densenet for histopathology image representation using TCGA diagnostic slides. Med Image Anal. 2021;70:102032.

    Article  Google Scholar 

  55. Yu M, Quan T, Peng Q, Yu X, Liu L. A model-based collaborate filtering algorithm based on stacked AutoEncoder. Neural Comput Appl. 2021;34:1–9.

    Google Scholar 

  56. Li YH, Putri WR, Aslam MS, Chang CC. Robust iris segmentation algorithm in non-cooperative environments using interleaved residual U-Net. Sensors. 2021;21(4):1434.

    Article  Google Scholar 

  57. Arora R, Saini I, Sood N. Modified UNet++ Model: A Deep Model for Automatic Segmentation of Lungs from Chest X-ray Images. In: 2021 2nd International Conference on Secure Cyber Computing and Communications (ICSCCC). IEEE 2021; pp. 166–169.

  58. Huang H et al. UNet 3+: A Full-Scale Connected UNet for Medical Image Segmenta- tion. In: ICASSP 2020—2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, pp. 1055–1059, https://doi.org/10.1109/ICASSP40776.2020.9053405.

  59. Wu X, Zhao L. Study on iris segmentation algorithm based on dense U-Net. IEEE Access. 2019;7:123959–68.

    Article  Google Scholar 

  60. Rapaka S, Rajesh Kumar P, Katta M, et al. A new segmentation method for non- ideal iris images using morphological reconstruction FCM based on improved DSA. SN Appl Sci. 2021;3:53. https://doi.org/10.1007/s42452-020-04110-1.

    Article  Google Scholar 

  61. Chen Y, Gan H, Zeng Z, Chen H. DADCNet: dual attention densely connected network for more accurate real iris region segmentation. Int J Intell Syst. 2022;37:829–58. https://doi.org/10.1002/int.22649.

    Article  Google Scholar 

  62. Jan F, Alrashed S, Min-Allah N. Iris segmentation for non-ideal iris biometric systems. Multimed Tools Appl. 2021. https://doi.org/10.1007/s11042-021-11075-9.

    Article  Google Scholar 

Download references

Funding

This research got no particular award from any subsidizing organization in general, business, or not-revenue driven areas.

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Jalpaiguri Government Engineering College, Jalpaiguri, 735102, India

    Ayan Banerjee & Chinmoy Ghosh

  2. Department of Information Technology, Kalyani Government Engineering College, Kalyani, 741235, India

    Satyendra Nath Mandal

Authors
  1. Ayan Banerjee
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chinmoy Ghosh
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Satyendra Nath Mandal
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ayan Banerjee.

Ethics declarations

Conflict of Interest

The creators pronounce that they have no irreconcilable circumstance.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Banerjee, A., Ghosh, C. & Mandal, S.N. Analysis of V-Net Architecture for Iris Segmentation in Unconstrained Scenarios. SN COMPUT. SCI. 3, 208 (2022). https://doi.org/10.1007/s42979-022-01113-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s42979-022-01113-0

Keywords

Search

Navigation