Combining Face with Face-Part Detectors under Gaussian Assumption

  • Andreas Uhl
  • Peter Wild
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7325)

Abstract

This paper addresses a simple and effective approach of face and face-part classifier fusion under Gaussian assumption, which is able to process heterogeneous visible wavelength (VW) and near infrared (NIR) image data. Evaluations using existing and publicly available Ada- Boost-based individual classifiers on the recently released CASIA-V4 iris distance database of close-up portrait images as well as on YaleB indicate, that (1) single classifiers are largely affected by the type of training data, especially for NIR and VW data, and therefore prone to errors, (2) by combining individual classifiers a more robust classifier is obtained, (3) processing time overhead is negligible, if individual classifiers exhibit a low false positive rate, and (4) the proposed fusion approach is not only able to reduce false positives, but also false negative detections.

Keywords

Face detection eye localization biometric fusion 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Aarabi, P., Lam, J., Keshavarz, A.: Face detection using information fusion. In: Proc. Int’l Conf. on Information Fusion, pp. 1–8 (2007)Google Scholar
  2. 2.
    Belaroussi, R., Milgram, M., Prevost, L.: Fusion of multiple detectors for face and eyes localization. In: Proc. Int’l Symp. Image and Signal Processing and Analysis (ISPA), pp. 24–29 (2005)Google Scholar
  3. 3.
    Belaroussi, R., Prevost, L., Milgram, M.: Multi-stage fusion for face localization. In: Proc. Int’l Conf. on Information Fusion, pp. 1–8 (2005)Google Scholar
  4. 4.
    Belhumeur, P., Jacobs, D., Kriegman, D., Kumar, N.: Localizing parts of faces using a consensus of exemplars. In: Proc. IEEE Conf. on Comp. Vis. and Pattern Rec (CVPR), pp. 545–552 (2011)Google Scholar
  5. 5.
    Burl, M., Leung, T.K., Perona, P.: Face localization via shape statistics. In: Workshop on Automatic Face and Gesture Recognition, pp. 1–6 (1995)Google Scholar
  6. 6.
    Cristinacce, D., Cootes, T., Scott, I.: A multi-stage approach to facial feature. In: Proc. Brit. Mach. Vis. Conf. (BMVC), pp. 231–240 (2004)Google Scholar
  7. 7.
    Gan, J.Y., Liang, Y.: A method for face and iris feature fusion in identity authentication. Int. J. Comp. Sci. Network Sec. 6(2), 135–138 (2006)Google Scholar
  8. 8.
    Georghiades, A.S., Belhumeur, P.N.: From few to many: Illumination cone models for face recognition under variable lighting and pose. IEEE Trans. Pattern Anal. Mach. Intell. 23(6), 643–660 (2001)CrossRefGoogle Scholar
  9. 9.
    Jin, L., Yuan, X., Satoh, S., Li, J., Xia, L.: A hybrid classifier for precise and robust eye detection. In: Proc. Int’l Conf. on Pattern Recognition (ICPR), pp. 731–735 (2006)Google Scholar
  10. 10.
    Kroon, B., Hanjalic, A., Maas, S.: Eye localization for face matching: is it always useful and under what conditions? In: Proc. Int’l Conf. on Content-based Image and Video Retrieval (CIVR), pp. 379–388 (2008)Google Scholar
  11. 11.
    Ma, Y., Ding, X., Wang, Z., Wang, N.: Robust precise eye location under probabilistic framework. In: Proc. Int’l. Conf. on Autom. Face and Gesture Rec., pp. 339–344 (2004)Google Scholar
  12. 12.
    Matey, J., Naroditsky, O., Hanna, K., Kolczynski, R., LoIacono, D., Mangru, S., Tinker, M., Zappia, T., Zhao, W.Y.: Iris on the move: Acquisition of images for iris recognition in less constrained environments. Proc. IEEE 94, 1936–1947 (2006)CrossRefGoogle Scholar
  13. 13.
    Micilotta, A., Jon, E., Bowden, O.: Detection and tracking of humans by probabilistic body part assembly. In: Proc. of British Machine Vision Conference (BMVC), pp. 429–438 (2005)Google Scholar
  14. 14.
    Nanni, L., Lumini, A.: A combination of face/eye detectors for a high performance face detection system. IEEE Multimedia PP(99), 1–15 (2011), http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6035655&isnumber=5255202 Google Scholar
  15. 15.
    Lienhart, R., Kuranov, A., Empirical, V.P.: analysis of detection cascades of boosted classifiers for rapid object. Tech. rep., Microproc. Res. Lab, Intel Labs (2002)Google Scholar
  16. 16.
    Saragih, J., Lucey, S., Cohn, J.: Face alignment through subspace constrained mean-shifts. In: Proc. Int’l Conf. on Computer Vision (ICCV), pp. 1034–1041 (2009)Google Scholar
  17. 17.
    Uhl, A., Wild, P.: Weighted adaptive hough and ellipsopolar transforms for real-time iris segmentation. In: Proc. Int’l Conf. on Biometrics (ICB), pp. 1–8 (to appear, 2012)Google Scholar
  18. 18.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. IEEE Conf. on Comp. Vis. and Pattern Rec (CVPR), pp. 511–518 (2001)Google Scholar
  19. 19.
    Wang, P., Green, M., Ji, Q., Wayman, J.: Automatic eye detection and its validation. In: Proc. IEEE Conf. on Comp. Vis. and Pattern Rec (CVPR), pp. 164–171 (2005)Google Scholar
  20. 20.
    Wang, Y., Tan, T., Jain, A.: Combining Face and Iris Biometrics for Identity Verification. In: Kittler, J., Nixon, M.S. (eds.) AVBPA 2003. LNCS, vol. 2688, pp. 805–813. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  21. 21.
    Wheeler, F., Perera, A., Abramovich, G., Yu, B., Tu, P.: Stand-off iris recognition system. In: Proc. IEEE Int’l Conf. on Biometrics: Theory, Applications and Systems (BTAS), pp. 1–7 (2008)Google Scholar
  22. 22.
    Xiao, Q.: Face detection using information fusion. In: IEEE Workshop on Comp. Intell. in Biometrics and Identity Mgmnt. (CIBIM), pp. 157–162 (2011)Google Scholar
  23. 23.
    Zhang, C., Zhang, Z.: A survey of recent advances in face detection. Tech. rep., Microsoft Research (2010), mSR-TR-2010-66Google Scholar
  24. 24.
    Zhang, Z., Wang, R., Pan, K., Li, S., Zhang, P.: Fusion of Near Infrared Face and Iris Biometrics. In: Lee, S.-W., Li, S.Z. (eds.) ICB 2007. LNCS, vol. 4642, pp. 172–180. Springer, Heidelberg (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Andreas Uhl
    • 1
  • Peter Wild
    • 1
  1. 1.Multimedia Signal Processing and Security Lab, Department of Computer SciencesUniversity of SalzburgAustria

Personalised recommendations