Iris Segmentation Using a Statistical Approach

  • Luis M. Zamudio-Fuentes
  • Mireya S. García-Vázquez
  • Alejandro A. Ramírez-Acosta
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6256)

Abstract

Eyelashes and reflections occluding the iris region are noise factors that degrade the performance of iris recognition. If these factors are not eliminated in iris segmentation phase, they are incorrectly considered as the iris region. Thus, produce false iris pattern information which decreases the recognition rate. In this paper a statistical approach is used to improve iris segmentation phase eliminating this noise from none constrain images, which is composed in three parts, finding the pupil and limbus boundary, reflection detection and eyelash detection. First an edge map is calculated using canny filter then the Circular Hough Transform is used to improve circle parameter finding. An intensity variation analysis is use to recognize a strong reflection. Eyelashes are classified in two categories, separable and multiple. Intensity variances are used to detect multiple eyelashes and an edge detector to localize separable eyelashes. The results show that statistics are useful to decide when is necessary applied the eyelash detector.

Keywords

Iris recognition biometric segmentation eyelash detector 

References

  1. 1.
    Daugman, J.: Results from 200 Billion iris Cross-Comparisons. Technical Report. UCAM-CL-TR-635, ISSN 1476-2986, Number 635 (June 2005)Google Scholar
  2. 2.
    Zamudio, L.M., García, M.S., Colores, J.M.: Revisión de las Etapas de Adquisición y Pre-Procesamiento de Imagen en un Sistema de Reconocimiento Basado en Iris. VI Taller-Escuela de Procesamiento de Imágenes PI09 CIMAT. Agosto, Gto. México (2009)Google Scholar
  3. 3.
    Xu, G.Z., Zhang, Z.F., Ma, Y.D.: Automatic Iris Segmentation Base on Local Areas. In: The 18th International Conference on Pattern Recognition (ICPR’06). IEEE, Los Alamitos (2006)Google Scholar
  4. 4.
    Kong, Z.: Detecting Eyelash and Reflection For Accurate Iris Segmentation. International Journal of Pattern Recognition and Artificial Intelligence 17(6), 1025–1034 (2003)CrossRefGoogle Scholar
  5. 5.
    Kang, P.: A Robust Eyelash Detection Based on Iris Focus Assessment. Pattern Recognition Letters 28, 1630–1639 (2007)CrossRefGoogle Scholar
  6. 6.
    Yuan, W.H.: A Novel Eyelash Detection Method for Iris Recognition. In: Proceeding on the 2005 IEEE. Engineering in Medicine and Biology 27th Annual Conference Shanghai, China, pp. 6536–6539 (2005)Google Scholar
  7. 7.
    Lim, S., Lee, K., Kim, J.: Efficient iris recognition by characterizing key local variations. IEEE Transactions on Image Processing 13(6) (June 2004)Google Scholar
  8. 8.
    Otero-Mateo, N., Vega-Rodríguez, M.Á., Gómez-Pulido, J.A., Sánchez-Pérez, J.M.: A Fast and Robust Iris Segmentation Method. In: Martí, J., Benedí, J.M., Mendonça, A.M., Serrat, J. (eds.) IbPRIA 2007. LNCS, vol. 4478, pp. 162–169. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  9. 9.
    Chen, Y., Wang, J., Han, C., Wang, L., Adjouadi, M.: A robust segmentation approach to iris recognition based on video. In: 37th IEEE Applied Imagery Pattern Recognition Workshop, pp. 1–8 (2008)Google Scholar
  10. 10.
    Rizon, M., Yazid, H., Saad, P., Shakaff, A.Y.M., Sugisaka, A.R.S.M., Yaacob, S., Rozailan Mamat, M., Karthigayan, M.: Object Detection using Circular Hough Transform. American Journal of Applied Sciences 2(12), 1606–1609 (2005) ISSN 1546-9239CrossRefGoogle Scholar
  11. 11.
    Hough TransformGoogle Scholar
  12. 12.
  13. 13.
    Hough TranformGoogle Scholar
  14. 14.
  15. 15.
    Gabor filter. Multiresolution Design of Multiple Gabor Filters for Texture Segmentation, wws2.uncc.edu/tpw/diss/diss.html
  16. 16.
    Kovesi, P.: Gabor filter and Log-Gabor filterGoogle Scholar
  17. 17.
  18. 18.
    Christmas, B.: Designing complex Gabor Filters (November 16, 2007), http://www.ee.surrey.ac.uk/CVSSP/Ravl/RavlDoc/share/doc/RAVL/html/Gabor.pdf
  19. 19.
    Multi Biometric Grand Challenge MBGC, face.nist.gov/mbgc/
  20. 20.
    Masek, L., Kovesi, P.: MATLAB Source Code for a Biometric Identification System Based on Iris Patterns. The School of Computer Science and Software Engineering. The University of Western Australia (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Luis M. Zamudio-Fuentes
    • 1
  • Mireya S. García-Vázquez
    • 1
  • Alejandro A. Ramírez-Acosta
    • 2
  1. 1.Centro de Investigación y Desarrollo de Tecnología Digital (CITEDI-IPN)TijuanaMéxico
  2. 2.MIRAL. R&DImperial BeachUSA

Personalised recommendations