CDIS: Circle Density Based Iris Segmentation

  • Anand Gupta
  • Anita Kumari
  • Boris Kundu
  • Isha Agarwal
Part of the Communications in Computer and Information Science book series (CCIS, volume 40)

Abstract

Biometrics is an automated approach of measuring and analysing physical and behavioural characteristics for identity verification. The stability of the Iris texture makes it a robust biometric tool for security and authentication purposes. Reliable Segmentation of Iris is a necessary precondition as an error at this stage will propagate into later stages and requires proper segmentation of non-ideal images having noises like eyelashes, etc. Iris Segmentation work has been done earlier but we feel it lacks in detecting iris in low contrast images, removal of specular reflections, eyelids and eyelashes. Hence, it motivates us to enhance the said parameters. Thus, we advocate a new approach CDIS for Iris segmentation along with new algorithms for removal of eyelashes, eyelids and specular reflections and pupil segmentation. The results obtained have been presented using GAR vs. FAR graphs at the end and have been compared with prior works related to segmentation of iris.

Keywords

Non Ideal Iris segmentation Circular Hough filter Sobel filter CASIA Eyelash Removal Specular Reflections Pupil Segmentation Canny Edge Eyelid Detection Eyelid Removal Non-ideal iris images 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bowyer, K.W., Hollingsworth, K., Flynn, P.J.: Image Understanding for Iris Biometrics: A Survey. Computer Vision and Image Understanding 110(2), 281–307 (2008)CrossRefGoogle Scholar
  2. 2.
    Ross, A., Shah, S.: Segmenting non-ideal irises using Geodesic Active Contours. In: Biometric Consortium Conference on Biometrics Symposium, pp. 1–6 (2006)Google Scholar
  3. 3.
    Youmaran, R., Xie, L.P., Adler, A.: Improved identification of iris and eyelash features. In: 24th Biennial Symposium on Communications, pp. 387–390 (2008)Google Scholar
  4. 4.
    Zhang, D., Monro, D.M., Rakshit, S.: Eyelash Removal method for human iris recognition. In: IEEE International Conference on Image Processing, pp. 285–288 (2006)Google Scholar
  5. 5.
    Daugman, J.: The importance of being random: Statistical Principles of iris recognition. Pattern Recognition 36(2), 279–291 (2003)CrossRefGoogle Scholar
  6. 6.
    Uzunova, V.I., Brömme, A.: An Eyelids and Eye Corners Detection and Tracking Method for Rapid Iris Tracking, Magdeburg (August 2005)Google Scholar
  7. 7.
    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
  8. 8.
    Caselles, V., Kimmel, R., Sapiro, G.: Geodesic Active Contours. International Journal of Computer Vision, 61–79 (1997)Google Scholar
  9. 9.
    Malladi, R., Sethian, J.A., Vemuri, B.C.: Shape Modelling with Front Propagation: A Level Set Approach. IEE Transactions on Parallel Analysis and Machine Intelligence, 158–175 (Feburary 1995)Google Scholar
  10. 10.
    Chinese Academy of Sciences Institute of Automation, CASIA, iris image database, www.cbsr.ia.ac.cn/Databases.htm
  11. 11.
    Iris Recognition by F. Cheung, Department of Computer Science and Electrical Engineering, The University of Queensland (B.Tech. Project thesis)Google Scholar
  12. 12.
    Imaging wiki - An Introduction to Smoothing, http://imaging.mrc-cbu.cam.ac.uk/imaging/PrinciplesSmoothing
  13. 13.
    Wikipedia, www.wikipedia.org
  14. 14.
    Matlab Online Help, www.mathworks.com
  15. 15.
    Wildes, R.: Iris Recognition: An Emerging Biometric Technology. Proceedings of the IEEE 85, 1348–1363 (1997)CrossRefGoogle Scholar
  16. 16.
    Camus, T.A., Wildes, R.: Reliable and fast eye finding in close-up images. In: IEEE 16th Int. Conf. on Pattern Recognition, vol. 1, pp. 389–394 (2002)Google Scholar
  17. 17.
    Access Excellence – The Eyes have it, http://www.accessexcellence.org/WN/SU/irisscan.php
  18. 18.
    Lankton, S., Tannenbaum, A.: Localizing Region-Based Active Contours. IEEE Transactions on Image Processing 17(11), 2029–2039 (2008)CrossRefPubMedPubMedCentralGoogle Scholar
  19. 19.
    Papandreou, G., Maragos, P.: Multigrid Geometric Active Contour Models. IEEE Transactions on Image Processing 16(1), 229–240 (2007)CrossRefPubMedGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Anand Gupta
    • 1
  • Anita Kumari
    • 1
  • Boris Kundu
    • 1
  • Isha Agarwal
    • 1
  1. 1.Department of Information Technology, Netaji Subhas Institute of TechnologyDelhi UniversityNew DelhiIndia

Personalised recommendations