Skip to main content
SpringerLink
Log in

Second-order convolutional networks for iris recognition

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Iris recognition in less constrained environments is challenging as the images taken therein contain severe noisy factors. How to represent iris texture for accurate and robust recognition in such environments is still an open issue. Towards addressing this problem, this paper proposes a novel convolutional network (ConvNet) for effective iris texture representation. The key of the proposed ConvNet is an interaction block which computes an affinity matrix among all pairwise high-level features for learning second-order relationships. The interaction block can model relationships of neighboring and long-range features, and is architecture-agnostic, suitable for different deep network architectures. To further improve the robustness of iris representation, we encode the affinity matrix based on ordinal measure. In addition, we develop a mask network corresponding to the feature learning network, which can exclude the noisy factors during iris matching. We perform thorough ablation studies to evaluate the effectiveness of the proposed networks. Experiments have shown that the proposed networks outperform state-of-the-art (SOTA) methods, achieving a false reject rate (FRR) of 5.49%, 10.41% and 5.80% at 10− 6 false accept rate (FAR) on ND-IRIS-0405, CASIA-IrisV4-Thousand and CASIA-IrisV4-Lamp respectively. And the improvements in equal error rates (EERs) are 0.41%, 0.72% and 0.40%, respectively, as compared with the SOTA methods.

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

References

  1. Biometrics Ideal Test. CASIA.v4 Database. Accessed: 2002. [online]. Available: http://biometrics.idealtest.org

  2. Adamović S, Miškovic V, Mač,ek N, Milosavljević M, Šarac M, Saračević M, Gnjatović M (2020) An efficient novel approach for iris recognition based on stylometric features and machine learning techniques. Futur Gener Comp Syst 107:144–157

    Article  Google Scholar 

  3. Barzut S, Milosavljević M, Adamović S, Saračević M, Mač,ek N, Gnjatović M (2021) A novel fingerprint biometric cryptosystem based on convolutional neural networks. Mathematics 9(7):730

    Article  Google Scholar 

  4. Carreira J, Caseiro R, Batista J, Sminchisescu C (2012) Semantic segmentation with second-order pooling. In: Eur. Conf. Comput. Vis., pp 430–443

  5. Daugman J (2001) Statistical richness of visual phase information: update on recognizing persons by iris patterns. Int J Comput Vis 45(1):25–38

    Article  Google Scholar 

  6. Daugman J (2006) Probing the uniqueness and randomness of iriscodes: Results from 200 billion iris pair comparisons. Proc IEEE 94(11):1927–1935

    Article  Google Scholar 

  7. Daugman J (2015) Information theory and the iriscode. IEEE Trans Inf Forensic Secur 11 (2):400–409

    Article  Google Scholar 

  8. Daugman JG (1993) High confidence visual recognition of persons by a test of statistical independence. IEEE Trans Pattern Anal Mach Intell 15(11):1148–1161

    Article  Google Scholar 

  9. Dong W, Sun Z, Tan T (2011) Iris matching based on personalized weight map. IEEE Trans Pattern Anal Mach Intell 33(9):1744–1757

    Article  Google Scholar 

  10. Dwivedi R, Dey S (2019) A novel hybrid score level and decision level fusion scheme for cancelable multi-biometric verification. Appl Intell 49(3):1016–1035

    Article  Google Scholar 

  11. Gangwar A, Joshi A (2016) Deepirisnet: Deep iris representation with applications in iris recognition and cross-sensor iris recognition. In: IEEE Int. Conf. Image process., pp 2301–2305

  12. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition.In: IEEE Conf. Comput. Vis. Pattern recog., pp 770–778

  13. Hermans A, Beyer L, Leibe B (2017) In defense of the triplet loss for person re-identification. arXiv:1703.07737

  14. Hu Y, Sirlantzis K, Howells G (2015) Exploiting stable and discriminative iris weight map for iris recognition under less constrained environment. In: IEEE Int. Conf. Biometrics: theory, Appl. Syst., pp 1–8

  15. Hu Y, Sirlantzis K, Howells G (2016) Optimal generation of iris codes for iris recognition. IEEE Trans Inf Forensic Secur 12(1):157–171

    Article  Google Scholar 

  16. Hu Y, Sirlantzis K, Howells G (2016) A study on iris textural correlation using steering kernels.In: IEEE Int. Conf. Biometrics: theory, Appl. Syst., pp 1–8

  17. Ionescu C, Vantzos O, Sminchisescu C (2015) Matrix backpropagation for deep networks with structured layers.In: Int. Conf. Comput. Vis., pp 2965–2973

  18. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks.In: Adv. Neural inform. Process. Syst., pp 1097–1105

  19. Li P, Liu X, Xiao L, Song Q (2010) Robust and accurate iris segmentation in very noisy iris images. Image Vis Comput 28(2):246–253

    Article  Google Scholar 

  20. Li P, Xie J, Wang Q, Gao Z (2018) Towards faster training of global covariance pooling networks by iterative matrix square root normalization.In: Int. Conf. Comput. Vis., pp 947–955

  21. Li P, Xie J, Wang Q, Zuo W (2017) Is second-order information helpful for large-scale visual recognition?.In: Int. Conf. Comput. Vis., pp 2070–2078

  22. Lin TY, RoyChowdhury A, Maji S (2017) Bilinear convolutional neural networks for fine-grained visual recognition. IEEE Trans Pattern Anal Mach Intell 40(6):1309–1322

    Article  Google Scholar 

  23. Liu N, Liu J, Sun Z, Tan T (2017) A code-level approach to heterogeneous iris recognition. IEEE Trans Inf Forensic Secur 12(10):2373–2386

    Article  Google Scholar 

  24. Liu N, Zhang M, Li H, Sun Z, Tan T (2016) Deepiris: Learning pairwise filter bank for heterogeneous iris verification. Pattern Recognit Lett 82:154–161

    Article  Google Scholar 

  25. Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation.In: IEEE Conf. Comput. Vis. Pattern recog., pp 3431–3440

  26. Matey JR, Naroditsky O, Hanna K, Kolczynski R, LoIacono DJ, Mangru S, Tinker M, Zappia TM, Zhao WY (2006) Iris on the move: Acquisition of images for iris recognition in less constrained environments. Proc IEEE 94(11):1936–1947

    Article  Google Scholar 

  27. Morampudi MK, Prasad MV, Raju U (2021) Privacy-preserving and verifiable multi-instance iris remote authentication using public auditor. Appl Intell:1–14

  28. Nguyen K, Fookes C, Sridharan S (2020) Constrained design of deep iris networks. IEEE Trans Image Process 29:7166–7175

    Article  Google Scholar 

  29. Othman N, Dorizzi B, Garcia-Salicetti S (2016) Osiris: An open source iris recognition software. Pattern Recognit Lett 82:124–131

    Article  Google Scholar 

  30. Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L et al (2019) Pytorch: an imperative style, high-performance deep learning library. In: Adv. Neural inform. Process. Syst., pp 8026–8037

  31. Phillips PJ, Scruggs WT, O’Toole AJ, Flynn PJ, Bowyer KW, Schott CL, Sharpe M (2009) Frvt 2006 and ice 2006 large-scale experimental results. IEEE Trans Pattern Anal Mach Intell 32(5):831–846

    Article  Google Scholar 

  32. Sánchez J, Perronnin F, Mensink T, Verbeek J (2013) Image classification with the fisher vector: Theory and practice. Int J Comput Vis 105(3):222–245

    Article  MathSciNet  Google Scholar 

  33. Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering.In: IEEE Conf. Comput. Vis. Pattern recog., pp 815–823

  34. Sun Z, Tan T (2008) Ordinal measures for iris recognition. IEEE Trans Pattern Anal Mach Intell 31(12):2211–2226

    Google Scholar 

  35. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions.In: IEEE Conf. Comput. Vis. Pattern recog., pp 1–9

  36. Tan CW, Kumar A (2013) Adaptive and localized iris weight map for accurate iris recognition under less constrained environments. In: IEEE Int. Conf. Biometrics: theory, Appl. Syst., pp 1–7

  37. Tang X, Xie J, Li P (2017) Deep convolutional features for iris recognition. In: Chin. Conf. Biom. Recog., pp 391–400

  38. Wang K, Kumar A (2019) Cross-spectral iris recognition using cnn and supervised discrete hashing. Pattern Recognit 86:85–98

    Article  Google Scholar 

  39. Wang K, Kumar A (2020) Periocular-assisted multi-feature collaboration for dynamic iris recognition. IEEE Trans. Inf. Forensic Secur 16:866–879

    Article  Google Scholar 

  40. Wang Q, Zhang X, Li M, Dong X, Zhou Q, Yin Y (2012) Adaboost and multi-orientation 2d gabor-based noisy iris recognition. Pattern Recognit Lett 33(8):978–983

    Article  Google Scholar 

  41. Weinberger KQ, Blitzer J, Saul LK (2006) Distance metric learning for large margin nearest neighbor classification. In: Adv. Neural inform. Process. Syst., pp 1473–1480

  42. Yang G, Zeng H, Li P, Zhang L (2015) High-order information for robust iris recognition under less controlled conditions. In: IEEE Int. Conf. Image process., pp 4535–4539

  43. Zhang Q, Li H, Sun Z, Tan T (2018) Deep feature fusion for iris and periocular biometrics on mobile devices. IEEE Trans Inf Forensic Secur 13(11):2897–2912

    Article  Google Scholar 

  44. Zhao Z, Kumar A (2017) Towards more accurate iris recognition using deeply learned spatially corresponding features. In: Int. Conf. Comput. Vis., pp 3809–3818

Download references

Acknowledgments

This research is supported by National Natural Science Foundation of China under grant no. 61971086 and 61471082.

Author information

Authors and Affiliations

  1. School of Information and Communication Engineering, Dalian University of Technology (DUT), Dalian, 116024, China

    Lingyao Jia, Xueyu Shi, Qiule Sun, Xingqiang Tang & Peihua Li

Authors
  1. Lingyao Jia
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xueyu Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Qiule Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xingqiang Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Peihua Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Peihua Li.

Additional information

Publisher’s note

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

Corresponding author: Peihua Li

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jia, L., Shi, X., Sun, Q. et al. Second-order convolutional networks for iris recognition. Appl Intell 52, 11273–11287 (2022). https://doi.org/10.1007/s10489-021-02925-y

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-021-02925-y

Keywords

Search

Navigation