An Unsupervised Approach for Eye Sclera Segmentation

  • Daniel Riccio
  • Nadia Brancati
  • Maria Frucci
  • Diego Gragnaniello
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10657)

Abstract

We present an unsupervised sclera segmentation method for eye color images. The proposed approach operates on a visible spectrum RGB eye image and does not require any prior knowledge such as eyelid or iris center coordinate detection. The eye color input image is enhanced by an adaptive histogram normalization to produce a gray level image in which the sclera is highlighted. A feature extraction process is involved both in the image binarization and in the computation of scores to assign to each connected components of the foreground. The binarization process is based on clustering and adaptive thresholding. Finally, the selection of foreground components identifying the sclera is performed on the analysis of the computed scores and of the positions between the foreground components. The proposed method was ranked \(2^{nd}\) in the Sclera Segmentation and Eye Recognition Benchmarking Competition (SSRBC 2017), providing satisfactory performance in terms of precision.

Keywords

Sclera segmentation Gray level clustering Feature extraction 

Notes

Acknowledgements

We would like to thank Dr. Abhijit Das of the University of Sydney for his authorization to publish sample images from the dataset of SSRBC 2017.

References

  1. 1.
  2. 2.
    Alkassar, S., Woo, W., Dlay, S., Chambers, J.: Enhanced segmentation and complex-sclera features for human recognition with unconstrained visible-wavelength imaging. In: 2016 International Conference on Biometrics (ICB), pp. 1–8. IEEE (2016)Google Scholar
  3. 3.
    Alkassar, S., Woo, W.L., Dlay, S.S., Chambers, J.A.: Robust sclera recognition system with novel sclera segmentation and validation techniques. IEEE Trans. Syst. Man Cybern.: Syst. 47(3), 474–486 (2017)CrossRefGoogle Scholar
  4. 4.
    Crihalmeanu, S., Ross, A., Derakhshani, R.: Enhancement and registration schemes for matching conjunctival vasculature. In: Tistarelli, M., Nixon, M.S. (eds.) ICB 2009. LNCS, vol. 5558, pp. 1240–1249. Springer, Heidelberg (2009).  https://doi.org/10.1007/978-3-642-01793-3_125 CrossRefGoogle Scholar
  5. 5.
    Das, A., Pal, U., Ballester, M.A.F., Blumenstein, M.: Fuzzy logic based selera recognition. In: 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), pp. 561–568. IEEE (2014)Google Scholar
  6. 6.
    Das, A., Pal, U., Ballester, M.A.F., Blumenstein, M.: Multi-angle based lively sclera biometrics at a distance. In: 2014 IEEE Symposium on Computational Intelligence in Biometrics and Identity Management (CIBIM), pp. 22–29. IEEE (2014)Google Scholar
  7. 7.
    Das, A., Pal, U., Blumenstein, M., Ballester, M.A.F.: Sclera recognition-a survey. In: 2013 2nd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 917–921. IEEE (2013)Google Scholar
  8. 8.
    De Marsico, M., Riccio, D.: A new data normalization function for multibiometric contexts: a case study. In: Campilho, A., Kamel, M. (eds.) ICIAR 2008. LNCS, vol. 5112, pp. 1033–1040. Springer, Heidelberg (2008).  https://doi.org/10.1007/978-3-540-69812-8_103 CrossRefGoogle Scholar
  9. 9.
    Derakhshani, R., Ross, A.: A texture-based neural network classifier for biometric identification using ocular surface vasculature. In: International Joint Conference on Neural Networks, IJCNN 2007, pp. 2982–2987. IEEE (2007)Google Scholar
  10. 10.
    Derakhshani, R., Ross, A., Crihalmeanu, S.: A new biometric modality based on conjunctival vasculature. In: Proceedings of Artificial Neural Networks in Engineering (ANNIE), pp. 1–8 (2006)Google Scholar
  11. 11.
    Jain, A.K., Murty, M.N., Flynn, P.J.: Data clustering: a review. ACM Comput. Surv. (CSUR) 31(3), 264–323 (1999)CrossRefGoogle Scholar
  12. 12.
    Radu, P., Ferryman, J., Wild, P.: A robust sclera segmentation algorithm. In: 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems (BTAS), pp. 1–6. IEEE (2015)Google Scholar
  13. 13.
    Thomas, N.L., Du, Y., Zhou, Z.: A new approach for sclera vein recognition. In: SPIE Defense, Security, and Sensing, p. 770805. International Society for Optics and Photonics (2010)Google Scholar
  14. 14.
    Zhou, Z., Du, E.Y., Thomas, N.L., Delp, E.J.: A new human identification method: sclera recognition. IEEE Trans. Syst. Man. Cybern.-Part A: Syst. Hum. 42(3), 571–583 (2012)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.University of Naples “Federico II”NaplesItaly
  2. 2.Institute for High Performance Computing and NetworkingNational Research Council of Italy (ICAR-CNR)NaplesItaly

Personalised recommendations