Quality-Based Super Resolution for Degraded Iris Recognition

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 318)

Abstract

In this paper we address the problem of low-quality iris recognition via super resolution approaches. We introduce two novel quality measures, onecomputed Globally (GQ) and the other Locally (LQ), for fusing at the pixel level(after a bilinear interpolation step) the images corresponding to several shots of a given person. These measures derive from a local GMM probabilistic characterization of good quality iris texture. We performed two types of experiments. The first oneconsiders low resolution video sequences coming from the MBGC portal database: it shows the superiority of our approach compared to score-based or average image-based fusion methods. Moreover, we show that the LQ-based fusionoutperforms the GQ-based fusion with a relative improvement of 4.79 % at the Equal Error Rate functioning point. The second experiment is performed on CASIA v4database containing sequences of still images with degraded quality resulting insevere segmentation errors. We show that the image fusion scheme improves greatly the performance and that the LQ-based fusion is mainly interesting for low FAR values.

Keywords

Iris recognition Video Quality Super resolution Fusion of images 

References

  1. 1.
    MBGC portal challenge version 2 preliminary results. http://www.nist.gov/itl/iad/ig/mbgc-presentations.cfm
  2. 2.
  3. 3.
    Hollingsworth, K., Peters, T., Bowyer, K.W., Flynn, P.J.: Iris recognition using signal-level fusion of frames from video. In: IEEE Transactions on Information Forensics and Security, vol. 4,  no. 4, pp. 837–848 (2009)Google Scholar
  4. 4.
    Fahmy, G.: Super-resolution construction of IRIS images from a visual low resolution  face video. In: Proceedings of the International Symposium on Signal Processing and Its Applications (2007)Google Scholar
  5. 5.
    Nguyen, K., Fookes, C.B., Sridharan, S., Denman, S.: Focus-score weighted super-resolution for uncooperative iris recognition at a distance and on the move. In: Proceedings of the International Conference of Image and Vision Computing (2010)Google Scholar
  6. 6.
    Nguyen, K., Fookes, C.B., Sridharan, S., Denman, S.: Quality-driven super-resolution for less constrained iris recognition at a distance and on the move. In: IEEE Transactions on Information Forensics and Security, vol. 6, no. 4, pp. 1248–1258 (2011)Google Scholar
  7. 7.
    Nguyen, K., Fookes, C.B., Sridharan, S., Denman, S.: Feature-domain super-resolution  for iris recognition. In: Proceedings of the International Conference on Image Processing (2011)Google Scholar
  8. 8.
    Jillela, R., Ross, A., Flynn, P.J.: Information fusion in low-resolution iris videos using principal components transform. In: Proceedings of the 2011 IEEE Workshop on Applications of  Computer Vision, pp. 262–269 (2011)Google Scholar
  9. 9.
    Cremer, S., Dorizzi, B., Garcia-Salicetti S., Lempiérière, N.: How a local quality measure can help improving iris recognition. In: Proceedings of the International Conference of the Biometrics Special Interest Group (2012)Google Scholar
  10. 10.
    Krichen, E., Garcia-Salicetti, S., Dorizzi, B.: A new probabilistic iris quality measure for comprehensive noise detection. In: Proceedings of the IEEE International Conference on Biometrics: Theory, Applications, and Systems, pp. 1–6 (2007)Google Scholar
  11. 11.
    Daugman, J.: How iris recognition works. IEEE Trans. Circuits Syst. Video Technol. 14, 21–30 (2007)CrossRefGoogle Scholar
  12. 12.
  13. 13.
    Sutra, G., Garcia-Salicetti, S., Dorizzi, B.: The viterbi algorithm at different resolutions for enhanced iris segmentation. In: Proceedings of the International Conference on  Biometrics, pp. 310–316 (2012)Google Scholar
  14. 14.
    Ma, L., Tan, T., Wang, Y., Zhang, D.: Efficient iris recognition by characterizing key local variations. IEEE Trans. Image Process. 13, 739–750 (2004)CrossRefGoogle Scholar
  15. 15.
    Krichen, E., Allano, L., Garcia-Salicetti, S., Dorizzi, B.: Specific texture analysis for iris recognition. Audio- and video-based biometric person authentication, pp. 23–30. Springer, Berlin (2005)CrossRefGoogle Scholar
  16. 16.

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Nadia Othman
    • 1
  • Nesma Houmani
    • 2
  • Bernadette Dorizzi
    • 1
  1. 1.CNRS UMR 5157 SAMOVARInstitut Mines-Télécom/Télécom SudParisEvryFrance
  2. 2.Laboratoire SIGMAESPCI-ParisTechParisFrance

Personalised recommendations