Skip to main content
Springer Nature Link
Log in

Enhancing human iris recognition performance in unconstrained environment using ensemble of convolutional and residual deep neural network models

  • Methodologies and Application
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

Despite the prominent advancements in iris recognition, unconstrained image acquisition through heterogeneous sensors has been a major obstacle in applying it for large-scale applications. In recent years, deep convolutional networks have achieved remarkable performance in the field of computer vision and have been employed in iris applications. In this study, three distinct models based on the ensemble of convolutional and residual blocks are proposed to enrich heterogeneous (cross-sensor) iris recognition. In order to analyze their quantitative performances, extensive experiments are carried out on two publicly available iris databases, ND-iris-0405 dataset and ND-CrossSensor-Iris-2013 dataset. Further, the final model has been scrutinized based on the least error rate and then fused using score-level fusion with two preeminent feature extraction methods, i.e., scale-invariant feature transform and binarized statistical information features. The resultant model is examined for cross-sensor iris recognition and reported the top two error rates as 1.01% and 1.12%. It infers that the proposed approach constitutes vital discerning iris features and can recognize that the micro-patterns exist inside the iris region. Furthermore, a comparative study is carried out with the state of the art, where the proposed approach obtains significantly improved performance.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Notes

  1. https://uidai.gov.in/’ Unique Identification Authority of India.

  2. https://www.amsterdam-airport.com/, Amsterdam Airport Schiphol (AMS).

  3. https://www.cbsa-asfc.gc.ca, Canada Border Services Agency.

References

  • Abiyev RH, Altunkaya K (2008) Personal iris recognition using neural network. Int J Secur Appl 2(2):41–50

    Google Scholar 

  • Ahuja K, Islam R, Barbhuiya FA et al (2017) Convolutional neural networks for ocular smartphone-based biometrics. Pattern Recognit Lett 91(3):17–26

    Google Scholar 

  • Al-Waisy S, Qahwaji R, Ipson S et al (2018) A multi-biometric iris recognition system based on a deep learning approach. Pattern Anal Appl 21(3):783–802

    MathSciNet  Google Scholar 

  • Arora S, Vatsa M, Singh R et al (2012) On iris camera interoperability. In: Proceeding IEEE international conference on biometrics: theory, applications, and systems, pp 346–352

  • Arya V, Gupta G (2014) Robust iris identification system using local descriptors. In: Proceeding international conference signal processing and integrated network (SPIN), pp 744–748

  • Baqar M, Azhar S, Iqbal Z, et al (2011) Efficient iris recognition system based on dual boundary detection using robust variable learning rate multilayer feed forward neural network. In: Information assurance and security (IAS), 7th international conference, pp 326–330

  • Barpanda S, Sa P, Marques O et al (2018) Iris recognition with tunable filter bank based feature. Multimed Tool Appl 77(6):7637–7674

    Google Scholar 

  • Bharathi S, Sudhakar R (2019) Biometric recognition using finger and palm vein images. Soft Comput 23(6):1843–1855

    Google Scholar 

  • Bock S, Goppold J, Weiß M (2018) An improvement of the convergence proof of the ADAM-optimizer. arXiv preprint arXiv:1804.10587

  • Bottou L (2010) Large-scale machine learning with stochastic gradient descent. In: Proceedings of COMPSTAT, Springer, Berlin, pp 177–186

  • Bowyer K, Flynn P (2009) The ND-IRIS-0405 iris image dataset. CoRR

  • Bowyer K, Baker S, Hentz A et al (2009) Factors that degrade the match distribution in iris biometrics. Identity Inf Soc 2(3):327–343

    Google Scholar 

  • Chen R, Lin X, Ding T (2011) Iris segmentation for non-cooperative recognition systems. IET Image Proc 5:448–456

    Google Scholar 

  • Choudhary M, Tiwari V, Venkanna U (2019) An approach for iris contact lens detection and classification using ensemble of customized DenseNet and SVM. Future Gener Comput Syst 101:1259–1270

    Google Scholar 

  • Connaughton R, Sgroi A, Bowyer K et al (2012) A multialgorithm analysis of three iris biometric sensors. IEEE Trans Inf Forensics Secur 7(3):919–931

    Google Scholar 

  • Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: IEEE computer society conference on computer vision and pattern recognition (CVPR’05), vol 1, pp 886–893

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

    Google Scholar 

  • Di Noia A, Martino A, Montanari P, Rizzi A (2019) Supervised machine learning techniques and genetic optimization for occupational diseases risk prediction. Soft Comput. https://doi.org/10.1007/s00500-019-04200-2

    Google Scholar 

  • Ding C, Tao D (2018) Trunk-branch ensemble convolutional neural networks for video-based face recognition. IEEE Trans Pattern Anal Mach Intell 40(4):1002–1014

    Google Scholar 

  • Fernandez FA, Gonzalez PT, Albacete VR, et al (2009) Iris recognition based on SIFT features. In: 2009 First IEEE international conference on biometrics, identity and security (BIdS), Tampa, FL, pp 1–8

  • Gangwar A, Joshi A (2016) DeepIrisNet: deep iris representation with applications in iris recognition and cross-sensor iris recognition. In: IEEE International conference on image processing (ICIP), Phoenix, AZ, pp 2301–2305

  • Grm K, Vitomir Š, Artiges A et al (2017) Strengths and weaknesses of deep learning models for face recognition against image degradations. IET Biometrics 7(1):81–89

    Google Scholar 

  • Gu H, Zhuang Y, Pan Y et al (2005) A new iris recognition approach for embedded system. In: Wu Z, Chen C, Guo M, Bu J (eds) Embedded software and systems. Springer, Heidelberg, pp 103–109

    Google Scholar 

  • Hajari K, Gawande U, Golhar Y (2016) Neural network approach to iris recognition in noisy environment. Procedia Comput Sci 78:675–682

    Google Scholar 

  • He K, Zhang X, Ren S, et al (2016) Identity mapping in deep residual network. In: Springer 14th European conference on computer vision (ECCV), Amsterdam, The Netherlands, pp 630–645

  • He K, Zhang X, Ren S, et al (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV, USA, pp 770–778

  • Hochreiter S, Younger AS, Conwell PR (2001) Learning to learn using gradient descent. In: International conference on artificial neural networks. Springer, Berlin, pp 87–94

  • Kim Y, Kim H, Kim S et al (2017) Illumination normalization using convolutional neural network with application to face recognition. Electron Lett 53(6):399–401

    Google Scholar 

  • Kokkinos I, Bronstein MM, Yuille A (2012) Dense scale invariant descriptors for images and surface. Research report rr-7914, INRIA

  • Li C, Zhou W, Yuan S (2015) Iris recognition based on a novel variation of local binary pattern. Vis Comput 31(10):1419–1429

    Google Scholar 

  • Liu N, Zhang M, Li H et al (2015) Deepiris: learning pairwise filter bank for heterogeneous iris verification. Pattern Recognit Lett 82(2):154–161

    Google Scholar 

  • Liu N, Liu J, Sun Z et al (2017) A code-level approach to heterogeneous iris recognition. IEEE Trans Inf Forensics Secur 12(10):2373–2386

    Google Scholar 

  • Lu B, Wu J, Wang Y (2010) An iris recognition algorithm based on ICA and SOM neural network. In: Image and signal processing (CISP), IEEE 3rd international congress, vol 5, pp 2445–2448

  • Menotti D, Chiachia G, Pinto A et al (2015) Deep representations for iris, face, and fingerprint spoofing detection. IEEE Trans Inf Forensics Secur 10(4):864–879

    Google Scholar 

  • Naderpour H, Mirrashid M (2019a) Shear failure capacity prediction of concrete beam-column joints in terms of ANFIS and GMDH. Pract Period Struct Des Constr 24:04019006. https://doi.org/10.1061/(asce)sc.1943-5576.0000417

    Google Scholar 

  • Naderpour H, Mirrashid M (2019b) Classification of failure modes in ductile and non-ductile concrete joints. Eng Fail Anal 103:361–375. https://doi.org/10.1016/j.engfailanal.2019.04.047

    Google Scholar 

  • Naderpour H, Mirrashid M, Nagai K (2019) An innovative approach for bond strength modeling in FRP strip-to-concrete joints using adaptive neuro-fuzzy inference system. Eng Comput. https://doi.org/10.1007/s00366-019-00751-y

    Google Scholar 

  • ND-CrossSensor-Iris-2013 (2013) [Available], https://sites.google.com/a/nd.edu/public-cvrl/data-sets

  • Ngo H, Rakvic R, Broussard R et al (2014) Resource-aware architecture design and implementation of hough transform for a real-time iris boundary detection system. IEEE Trans Consum Electron 60(3):485–492

    Google Scholar 

  • Nguyen K, Fookes C, Ross A et al (2018) Iris recognition with off-the-shelf CNN features: a deep learning perspective. IEEE Access 6:18848–18855

    Google Scholar 

  • Okokpujie K, Noma-Osaghae E, John S et al (2017) An improved iris segmentation technique using circular hough transform. In: Lecture notes in electrical engineering, Springer, Berlin, p 450

  • Ortiz E, Bowyer K, Flynn P (2016) Dilation-aware enrolment for iris recognition. IET Biometrics 5(2):92–99

    Google Scholar 

  • Poster D, Nasrabadi N, Riggan B (2018) Deep sparse feature selection and fusion for textured contact lens detection. In: Proceeding of international conference of the biometrics special interest group (BIOSIG), Darmstadt, pp 1–5

  • Radman A, Jumari K, Zainal N (2013) Fast and reliable iris segmentation algorithm. IET Image Proc 7(1):42–49

    Google Scholar 

  • Raghavendra R, Busch C (2015) Robust scheme for iris presentation attack detection using multiscale binarized statistical image features. IEEE Trans Inf Forensics Secur 10(4):703–715

    Google Scholar 

  • Rahulkar D, Waghmare L, Holambe R (2014) A new approach to the design of hybrid finer directional wavelet filter bank for iris feature extraction and classification using k-out-of-n: a post-classifier. Pattern Anal Appl 17(3):529–547

    MathSciNet  Google Scholar 

  • Rai H, Yadav A (2014) Iris recognition using combined support vector machine and Hamming distance approach. Expert Syst Appl 41(2):588–593

    Google Scholar 

  • Ramaiah N, Kumar A (2017) Towards more accurate iris recognition using cross-spectral matching. IEEE Trans Image Process 26:208–221

    MathSciNet  MATH  Google Scholar 

  • Rathgeb C, Uhl A, Wild P (2013) Iris recognition: from segmentation to template security. In: Advances in information security. Springer, Berlin, 59

  • Roy K, Bhattacharya P (2005) Iris recognition with support vector machines. In: Advances in biometrics. Springer, Berlin, pp. 486–492

  • Sarhan AM (2009) Iris recognition using the discrete cosine transform and artificial neural networks. J Comput Sci 5(4):369–373

    Google Scholar 

  • Scherer D, Muller A, Behnke S (2010) Evaluation of pooling operations in convolutional architectures for object recognition. In: International conference on artificial neural networks (ICANN), of lecture notes in computer science. Springer, Berlin, pp 92–101

  • Sivasankar E, Selvi C, Mahalakshmi S (2019) Rough set-based feature selection for credit risk prediction using weight-adjusted boosting ensemble method. Soft Comput. https://doi.org/10.1007/s00500-019-04167-0

    Google Scholar 

  • Srivastava N, Hinton G, Krizhevsky A et al (2014) ‘Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958

    MathSciNet  MATH  Google Scholar 

  • Tania U, Motakabber S, Ibrahimy M (2014) Template matching techniques for iris recognition system. In: International conference on computer and communication engineering, Kuala Lumpur, pp 9–11

  • Tolosana R, Vera-Rodriguez R, Fierrez J, Ortega-Garcia J (2018) Exploring recurrent neural networks for on-line handwritten signature biometrics. IEEE Access 6:5128–5138

    Google Scholar 

  • Trokielewicz M, Bartuzi E (2018) Cross-spectral iris recognition for mobile applications using high-quality color images. J Telecommun Inf Technol 3:91–97

    Google Scholar 

  • Tsai C, Lin H, Taur J, Tao C (2012) Iris recognition using possibilistic fuzzy matching on local features. IEEE Trans Syst Man Cybern Part B (Cybernetics) 42(1):150–162

    Google Scholar 

  • Wang K, Kumar A (2019) Toward more accurate iris recognition using dilated residual features. IEEE Trans Inf Forensics Secur 14(12):3233–3245

    Google Scholar 

  • Wang Z, Li C, Shao H et al (2018) ‘Eye recognition with mixed convolutional and residual network (MiCoRe-Net). IEEE Access 6:17905–17912

    Google Scholar 

  • Winston JJ, Hemanth DJ (2019) A comprehensive review on iris image-based biometric system. Soft Comput 23:9361–9384. https://doi.org/10.1007/s00500-018-3497-y

    Google Scholar 

  • Yadav D, Kohli N, Doyle JS et al (2014) Unraveling the effect of textured contact lenses on iris recognition. IEEE Trans Inf Forensics Secur 9(5):851–862

    Google Scholar 

  • Zhao Z, Kumar A (2018) Improving periocular recognition by explicit attention to critical regions in deep neural network. IEEE Trans Inf Forensics Secur 13(12):2937–2952

    Google Scholar 

  • Zhao Z, Kumar A (2019) A deep learning based unified framework to detect, segment and recognize irises using spatially corresponding features. Pattern Recognit 93:546–557

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. DSPM IIIT Naya Raipur (C.G.), Naya Raipur, 493661, India

    Meenakshi Choudhary, Vivek Tiwari & U. Venkanna

Authors
  1. Meenakshi Choudhary
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Vivek Tiwari
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. U. Venkanna
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Vivek Tiwari.

Ethics declarations

Conflict of interest

There is no funding provided for this research work, and none of the authors having any conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Additional information

Communicated by V. Loia.

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

Choudhary, M., Tiwari, V. & Venkanna, U. Enhancing human iris recognition performance in unconstrained environment using ensemble of convolutional and residual deep neural network models. Soft Comput 24, 11477–11491 (2020). https://doi.org/10.1007/s00500-019-04610-2

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-019-04610-2

Keywords