Skip to main content
SpringerLink
Log in

Iris Recognition Based on Fine-Tune SquIrisNet

  • APPLIED PROBLEMS
  • Published:
Pattern Recognition and Image Analysis Aims and scope Submit manuscript

Abstract

Convolutional neural networks (CNN) have achieved unprecedented results in the fields of pattern recognition and image processing. CNN methods have also been gradually applied to iris recognition. However, in the case of insufficient training samples, training deep CNN models is prone to overfitting. In order to solve the above problem, this paper proposes an iris recognition method based on fine-tune SquIrisNet. When the pre-trained SqueezNet is migrated to the iris dataset, the fully connected layers are used instead of the convolutional layer and the global pooling layer, then the parameters are adjusted using the error back propagation algorithm, and finally the images are classified by the Softmax classifier. The fully connected layers added in this model can play the role of “firewall” in the fine-tune process, retaining the model complexity to a certain extent. The experimental results on the IIT Delhi and SDUMLA-HMT iris databases show that the proposed method has higher correct recognition rate, faster convergence speed and better robustness than AlexNet and VGGNet.

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.

Similar content being viewed by others

REFERENCES

  1. J. Daugman, “Iris recognition border-crossing system in the UAE,” Int. Airport Rev. 8 (2) (2004).

  2. R. P. Wildes, J. C. Asmuth, G. L. Green, et al., “A machine-vision system for iris recognition,” Mach. Vision Appl. 9 (1), 1–8 (1996).

    Article  Google Scholar 

  3. W. W. Boles, “A security system based on human iris identification using wavelet transform,” Eng. Appl. Artif. Intell. 11 (1), 77–85 (1998).

    Article  Google Scholar 

  4. C. Belcher and Y. Du, “Region-based SIFT approach to iris recognition,” Opt. Lasers Eng. 47 (1), 139–147 (2009).

    Article  Google Scholar 

  5. D. M. Monro, S. Rakshit, and D. Zhang, “DCT-based iris recognition,” IEEE Trans. Pattern Anal. Mach. Intell. 29 (4), 586–595 (2007).

    Article  Google Scholar 

  6. K. Miyazawa, K. Ito, T. Aoki, et al., “An effective approach for iris recognition using phase-based image matching,” IEEE Trans. Pattern Anal. Mach. Intell. 30 (10), 1741–1756 (2008).

    Article  Google Scholar 

  7. A. Bastys, J. Kranauskas, and R. Masiulis, “Iris recognition by local extremum points of multiscale Taylor expansion,” Pattern Recognit. 42 (9), 1869–1877 (2009).

    Article  Google Scholar 

  8. A. Sharif Razavian, H. Azizpour, J. Sullivan, et al., “CNN features off-the-shelf: An astounding baseline for recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (2014), pp. 806–813.

  9. A. Gangwar and A. Joshi, “DeepIrisNet: Deep iris representation with applications in iris recognition and cross-sensor iris recognition,” in 2016 IEEE International Conference on Image Processing (ICIP) (2016), pp. 2301–2305.

  10. S. Minaee, A. Abdolrashidiy, and Y. Wang, “An experimental study of deep convolutional features for iris recognition,” in 2016 IEEE Signal Processing in Medicine and Biology Symposium (SPMB) (2016), pp. 1–6.

  11. Z. Zhao and A. Kumar, “Towards more accurate iris recognition using deeply learned spatially corresponding features,” in Proceedings of the IEEE International Conference on Computer Vision (2017), pp. 3809–3818.

  12. Y. Chen, W. Wang, Z. Zeng, et al., Adapted deep convnets technology for robust iris recognition,” J. Electron. Imaging 28 (3), 033008 (2019).

    Google Scholar 

  13. O. Russakovsky, J. Deng, H. Su, et al., “ImageNet large scale visual recognition challenge,” Int. J. Comput. Vision 115 (3), 211–252 (2015).

    Article  MathSciNet  Google Scholar 

  14. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” in Advances in Neural Information Processing Systems (2012), pp. 1097–1105.

    Google Scholar 

  15. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition” (2014). arXiv:1409.1556 [cs.CV].

  16. F. N. Iandola, S. Han, M. W. Moskewicz, et al., “SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size” (2016). arXiv:1602.07360.

  17. Mu Jun, Yan Jun-feng, and Peng Qing-hua, “Iris localization for visible-light images based on Hough transform,” Comput. Technol. Dev. 27 (5), 40–45 (2017).

    Google Scholar 

  18. J. G. Daugman, “High confidence visual recognition of persons by a test of statistical independence,” IEEE Trans. Pattern Anal. Mach. Intell. 15 (11), 1148–1161 (1993).

    Article  Google Scholar 

  19. Y. Chen, F. Yang, and H. Chen, “An effective iris recognition system based on combined feature extraction and enhanced support vector machine classifier,” J. Inf. Comput. Sci. 10 (17), 5505–5519 (2013).

    Article  Google Scholar 

  20. K. He and J. Sun, “Convolutional neural networks at constrained time cost,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015), pp. 5353–5360.

  21. K. He, X. Zhang, S. Ren, et al., “Deep residual learning for image recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016), pp. 770–778.

  22. C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going deeper with convolutions,” in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015).

  23. C. L. Zhang, J. H. Luo, X. S. Wei, et al., “In defense of fully connected layers in visual representation transfer,” in Pacific Rim Conference on Multimedia (Springer, Cham, 2017), pp. 807–817.

  24. Y. Yin, L. Liu, and X. Sun, “SDUMLA-HMT: A multimodal biometric database,” in Chinese Conference on Biometric Recognition (Springer, Berlin, Heidelberg, 2011), pp. 260–268.

  25. A. Kumar and A. Passi, “Comparison and combination of iris matchers for reliable personal authentication,” Pattern Recognit. 43 (3), 1016–1026 (2010).

    Article  Google Scholar 

  26. G. E. Hinton, S. Osindero, and Y. W. Teh, “A fast learning algorithm for deep belief nets,” Neural Comput. 18 (7), 1527–1554 (2006).

    Article  MathSciNet  Google Scholar 

  27. S. Yan, Understanding LSTM networks. Accessed August 11, 2015.

  28. W. Zaremba, I. Sutskever, and O. Vinyals, “Recurrent neural network regularization” (2014). arXiv:1409.2329

Download references

ACKNOWLEDGMENTS

We thank the anonymous referees for their thorough reviews and constructive comments. The research in this paper uses the IIT Delhi Iris Database provided by Indian Institute of Technology Delhi.

Funding

This research is supported by Science and technology development plan project of Jilin Province (grant no. 20180520017JH), Science and technology project of the Jilin Provincial Education Department (grant no. JJKH20180448KJ), Jilin Province Industrial Innovation Special Fund Project (grant no. 2019C053-2).

Author information

Authors and Affiliations

  1. School of Computer Science, Northeast Electric Power University, 132012, Jilin, China

    Guang Huo, Huan Guo, Qi Zhang & Wenyu Li

  2. School of Foreign Languages, Northeast Electric Power University, 132012, Jilin, China

    Yangrui Zhang

  3. College of Computer Science and Technology, Jilin University, 130012, Changchun, China

    Yuanning Liu

Authors
  1. Guang Huo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Huan Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yangrui Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yuanning Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Qi Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Wenyu Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Guang Huo, Huan Guo, Yangrui Zhang, Yuanning Liu, Qi Zhang or Wenyu Li.

Ethics declarations

The authors declare that they have no conflicts of interest.

Additional information

Guang Huo received his PhD degree from the College of Computer Science and Technology, Jilin University, China, in 2016. He is an associate professor and supervisor of Master with Northeast Electric Power University. His research interests include pattern recognition, machine learning, biometrics, and image processing.

Huan Guo (March 13, 1994), Native place: Changchun Jilin (province), currently a second-year of postgraduate at the School of Computer Science and Technology, Northeast Electric Power University, China. Her research interests is iris recognition.

Yangrui Zhang was born in Jilin, China in 1981. She received his M.A. degrees from the School of Foreign languages at Northeast Normal University in China in 2006. She is a senior lecturer with the School of Foreign languages at Northeast Electric Power University. Her research interests include linguistics, semantic analysis, and machine learning.

Yuanning Liu received the Ph.D. degree from Jilin University, China, in 2004. He completed the Ph.D. Research with the University of Vienna, Austria, in 2007. He was a Visiting Scholar with the University of Missouri, USA, in 2015. He is currently a Professor in computer science with Jilin University. His research interests include software engineering, iris biometrics, pattern recognition, and bioinformatics.

Qi Zhang (April 15, 1992), Native place: Changchun Jilin (province), currently a third-year of postgraduate at the School of Computer Science and Technology, Northeast Electric Power University, China. Her research interests is iris recognition.

Wenyu Li (July 6, 1994), Native place: Anshan Liaoning (province), currently a second-year of postgraduate at the School of Computer Science and Technology, Northeast Electric Power University, China. Her research interests is iris recognition.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Guang Huo, Guo, H., Zhang, Y. et al. Iris Recognition Based on Fine-Tune SquIrisNet. Pattern Recognit. Image Anal. 31, 72–80 (2021). https://doi.org/10.1134/S1054661821010107

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S1054661821010107

Keywords:

Search

Navigation