Advertisement

Eyelid Position Detection Method for Mobile Iris Recognition

  • Gleb OdinokikhEmail author
  • Mikhail Korobkin
  • Vitaly Gnatyuk
  • Vladimir Eremeev
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 794)

Abstract

Information about eyelid position in an image is used during iris recognition for eyelid and eyelash noise removal, iris image quality estimation and other purposes. Eyelid detection is usually performed after iris-sclera boundary localization which is a fairly complex operation itself. If the authentication is working on a hand-held device, this order is not always justified, mainly because of the device limited performance, user interaction difficulties and highly variable environmental conditions. In this case the eyelid position information could be used to determine whether the image should be passed for the further complex processing operations. This paper proposes a method of eyelid position detection for iris image quality estimation and further complete eyelid border localization and compares its performance with several similar existing methods on four open datasets.

Keywords

Eyelid detection Mobile biometrics Iris recognition 

References

  1. 1.
    Daugman, J.: How iris recognition works. IEEE Trans. Circuits Syst. Video Technol. 14(1), 21–30 (2004).  https://doi.org/10.1109/TCSVT.2003.818350CrossRefGoogle Scholar
  2. 2.
    Chowhan, S., Shinde, G.: Iris biometrics recognition application in security management. In: Congress on Image and Signal Processing (CISP 2008), vol 1, pp. 661–665 (2008).  https://doi.org/10.1109/CISP.2008.766
  3. 3.
    Bhattacharya, V., Mali, K.: Iris as a biometric feature: application, recognition, advantages & shortcomings. Int. J. Adv. Res. 3(6), 1410–1415 (2013)Google Scholar
  4. 4.
    Dorairaj, V., Schmidt, N.A., Fahmy, G.: Performance evaluation of non-ideal iris based recognition system implementing global ICA encoding. In: IEEE International Conference on Image Processing (ICIP 2004), vol 3, pp. 11–14 (2004).  https://doi.org/10.1109/ICIP.2005.1530384
  5. 5.
    Wildes, R.: Iris recognition: an emerging biometric technology. Proc. IEEE 85(9), 1348–1363 (1997).  https://doi.org/10.1109/5.628669CrossRefGoogle Scholar
  6. 6.
    Zhang, X., Wang, Q., Zhu, H., Yao, C., Gao, L., Liu, X.: Noise detection of iris image based on texture analysis. In: Chinese Control and Decision Conference Proceedings (CCDC 2009), pp. 2366–2370 (2009).  https://doi.org/10.1109/CCDC.2009.5192665
  7. 7.
    Adam, M., Rossant, F., Amiel, F., Mikovicova, B., Ea, T.: Reliable eyelid localization for iris recognition. In: Blanc-Talon, J., Bourennane, S., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2008. LNCS, vol. 5259, pp. 1062–1070. Springer, Heidelberg (2008).  https://doi.org/10.1007/978-3-540-88458-3_96 CrossRefGoogle Scholar
  8. 8.
    Gankin, K.A., Gneusev, A.N., Matveev, I.A.: Iris image segmentation based on approximate methods with subsequent refinements. J. Comput. Syst. Sci. Int. 53(2), 224–238 (2014).  https://doi.org/10.1134/S1064230714020099CrossRefzbMATHGoogle Scholar
  9. 9.
    Solomatin, I., Matveev, I.: Detecting visible areas of iris by qualifier of local textural features. J. Mach. Learn. Data Anal. 1(14), 1919–1929 (2016).  https://doi.org/10.21469/22233792.1.14.03CrossRefGoogle Scholar
  10. 10.
    Min, T.-H., Park, R.-H.: Comparison of eyelid and eyelash detection algorithms for performance improvement of iris recognition. In: 15th IEEE International Conference on Image Processing (ICIP 2008), pp. 257–260 (2008)  https://doi.org/10.1109/ICIP.2008.4711740
  11. 11.
    Masek, L.: Recognition of human iris patterns for biometric identification. Measurement 32(8), 1502–1516 (2003)Google Scholar
  12. 12.
    Kang, B., Park, K.: A robust eyelash detection based on iris focus assessment. Pattern Recogn. Lett. 28(13), 1630–1639 (2007).  https://doi.org/10.1016/j.patrec.2007.04.004CrossRefGoogle Scholar
  13. 13.
    Adam, M., Rossant, F., Amiel, F., Mikovikova, B., Ea, T.: Eyelid localization for iris identification. Radioengineering 17(4), 82–85 (2008)Google Scholar
  14. 14.
    Yang, L., Wu, T., Dong, Y., Fei, L.: Eyelid localization using asymmetric Canny operator. In: Proceedings of International Conference on Computer Design and Applications, pp. 533–535 (2010)Google Scholar
  15. 15.
    Kim, H., Cha, J., Lee, W.: Eye detection for gaze tracker with near infrared illuminator. In: 17th IEEE International Conference on Computational Science and Engineering (CSE 2014), pp. 458–464 (2014).  https://doi.org/10.1109/CSE.2014.111
  16. 16.
    He, Z., Tan, T., Sun, Z., Qiu, X.: Robust eyelid, eyelash and shadow localization for iris recognition. In: 15th IEEE International Conference on Image Processing (ICIP 2008), pp. 265–268 (2008).  https://doi.org/10.1109/ICIP.2008.4711742
  17. 17.
  18. 18.
  19. 19.
    AOptix Iris Database. http://www.aoptix.com
  20. 20.
    The BTAS Competition on Mobile Iris Recognition. http://biometrics.idealtest.org/2016/MIR2016.jsp

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Gleb Odinokikh
    • 1
    • 3
    Email author
  • Mikhail Korobkin
    • 2
  • Vitaly Gnatyuk
    • 3
  • Vladimir Eremeev
    • 3
  1. 1.Federal Research Center “Computer Science and Control” of the Russian Academy of SciencesMoscowRussia
  2. 2.National Research University of Electronic TechnologyZelenogradRussia
  3. 3.Samsung R&D Institute Russia (SRR)MoscowRussia

Personalised recommendations