Detecting Precise Iris Boundaries by Circular Shortest Path Method

Ivan Matveev, Ivan Simonenko

Abstract

Modified circular shortest path detection method is applied for refining pupil and iris boundaries using given approximate pupil and iris circles. Brightness gradient direction is employed to choose image pixels, which may belong to pupil or iris boundary. Using initial approximate circles allows the method to work in a narrow ring, which contains only single circular contour. Under these conditions the method allows to correctly handle almost all images used for iris recognition tasks and appears to be more precise than human expert in marking the pupil border. The method was tested with public domain iris databases, containing more than 80000 images totally.

References

  1. ISO/IEC 19794-6:2005 Information technology - Biometric data interchange formats - Part 6: Iris image data, 2005.
  2. Kansky, J.J.: Clinical Ophthalmology: a Systematic Approach, Elsevier, London, 2003.
  3. Bowyer, K., Hollingsworth, K., and Flynn, P.: Image understanding for iris biometrics: A survey // Computer Vision and Image Understanding. 2008. P.281-307.
  4. Bowyer, K., Hollingsworth, K., and Flynn, P.: A survey of iris biometrics research: 2008- 2010 // Handbook of Iris Recognition, Mark Burge and Kevin W. Bowyer, editors. Springer. 2012.
  5. He, Z., Tan, T., Sun, Z., and Qiu, X. Toward accurate and fast iris segmentation for iris biometrics. In IEEE PAMI. 2009. V.31. P.1670-1684.
  6. Maenpaa, T. An iterative algorithm for fast iris detection. In Int. Workshop on Biometric Recognition Systems. Beijing. China.. 2005. P.127.
  7. Nabti, M., Ghouti, L., and Bouridane, A. An effective and fast iris recognition system based on a combined multiscale feature extraction technique. In Pattern Recognition. 2008. V.41. P.868-879.
  8. Pan, L., Xie, M., and Ma, Z. Iris localization based on multiresolution analysis. In Proc. 19th Intern. Conf. Pattern Recognition. Tampa, Florida, USA.. 2008. P.1-4.
  9. Daugman, J.: New methods in iris recognition // IEEE Trans. on Systems, Man and Cybernetics. Part B: Cybernetics. 2007. V.37. P.1167-1175.
  10. Ross, A., Shah, S.: Segmenting non-ideal iris using geodesic active contours // Biometrics Symposium: Special Session on Research at the Biometric Consortium Conf. Baltimore. USA, 2006. P.16.
  11. Koh, J., Govindaraju, V., Chaudhary, V.: A robust iris localization method using an active contour model and hough transform // 20th Int. Conf. on Pattern Recognition. Istanbul. Turkey. 2010. P.2852-2856.
  12. Sun, C., Pallottino, S.: Circular shortest path in images // Pattern Recognition. 2003. V.36. N.3. P.709-719.
  13. Matveev, I.A.: Circular Shortest Path as a Method of Detection and Refinement of Iris Borders in Eye Image // Journal of Computer and Systems Sciences International. 2011. V.50. N.5. P.778-784.
  14. Proenca, H., Alexandre, L.A.: UBIRIS: A noisy iris image database // 13th Intern. Conf. on Image Analysis and Processing. V.3617. Cagliari, Italy: Springer, 2005. P.970-977.
  15. Chinese academy of sciences institute of automation (CASIA), CASIA Iris image database http://www.cbsr.ia.ac.cn/IrisDatabase.htm, 2005.
  16. Phillips, P.J., Scruggs, W.T., O'Toole, A.J. et al. Frvt2006 and ice2006 large-scale experimental results // IEEE PAMI. 2010. V.32. .5. P.831-846.
  17. Masek, L.: Recognition of human iris patterns for biometric identification. http://www.csse.uwa.edu.au/ pk/studentprojects/libor, 2003.
  18. Matveev, I.A.: Detection of Iris in Image By Interrelated Maxima of Brightness Gradient Projections // Applied and Computational Mathematics, 2010, V.9, No.2, pp.252-257.
Download


Paper Citation


in Harvard Style

Matveev I. and Simonenko I. (2013). Detecting Precise Iris Boundaries by Circular Shortest Path Method . In Proceedings of the 4th International Workshop on Image Mining. Theory and Applications - Volume 1: IMTA-4, (VISIGRAPP 2013) ISBN 978-989-8565-50-1, pages 101-108. DOI: 10.5220/0004394501010108


in Bibtex Style

@conference{imta-413,
author={Ivan Matveev and Ivan Simonenko},
title={Detecting Precise Iris Boundaries by Circular Shortest Path Method},
booktitle={Proceedings of the 4th International Workshop on Image Mining. Theory and Applications - Volume 1: IMTA-4, (VISIGRAPP 2013)},
year={2013},
pages={101-108},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004394501010108},
isbn={978-989-8565-50-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Workshop on Image Mining. Theory and Applications - Volume 1: IMTA-4, (VISIGRAPP 2013)
TI - Detecting Precise Iris Boundaries by Circular Shortest Path Method
SN - 978-989-8565-50-1
AU - Matveev I.
AU - Simonenko I.
PY - 2013
SP - 101
EP - 108
DO - 10.5220/0004394501010108