Novel Adaptive Eye Detection and Tracking for Challenging Lighting Conditions

  • Mahdi Rezaei
  • Reinhard Klette
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7729)


The paper develops a novel technique that significantly improves the performance of Haar-like feature-based object detectors in terms of speed, detection rate under difficult lighting conditions, and reduced number of false-positives. The method is implemented and validated for driver monitoring under very dark, very bright, and normal conditions. The framework includes a fast adaptive detector designed to cope with rapid lighting variations, as well as an implementation of a Kalman filter for reducing the search region and indirect support of eye monitoring and tracking. The proposed methodology effectively works under low-light conditions without using infrared illumination or any other extra lighting support. Experimental results, performance evaluation, and comparing a standard Haar-like detector with the proposed adaptive eye detector, show noticeable improvements.


Face Detection False Detection Search Region Face Tracking Yale Database 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
  2. 2.
    Brandt, T., Stemmer, R., Rakotonirainy, A.: Affordable visual driver monitoring system for fatigue and monotony. Systems Man Cybernetics 7, 6451–6457 (2004)Google Scholar
  3. 3.
    FERET Face Database (2012),
  4. 4.
    Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Computer System Sciences 55, 119–139 (1997)MathSciNetzbMATHCrossRefGoogle Scholar
  5. 5.
    Face of tomorrow database (2012),
  6. 6.
    Hsu, R., Abdel-Mottaleb, M., Jain, A.K.: Face detection in color images. IEEE Trans. Pattern Analysis and Machine Intelligence 24, 696–706 (2002)CrossRefGoogle Scholar
  7. 7.
    Jesorsky, O., Kirchberg, K.J., Frischholz, R.W.: Robust Face Detection Using the Hausdorff Distance. In: Bigun, J., Smeraldi, F. (eds.) AVBPA 2001. LNCS, vol. 2091, pp. 90–95. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  8. 8.
    Kalman, R.E.: A new approach to linear filtering and prediction problems. J. Basic Engineering 82, 35–45 (1960)CrossRefGoogle Scholar
  9. 9.
    Li, S.Z., Jian, A.K.: Handbook of Face Recognition. Springer, London (2011)zbMATHCrossRefGoogle Scholar
  10. 10.
    Majumdar, A.: Automatic and robust detection of facial features in frontal face images. In: Proc. Int. Conf. Computer Modelling Simulation, pp. 331–336 (2011)Google Scholar
  11. 11.
    World recognized Haar classifier contributors for face and eye detection (2012),
  12. 12.
    Tsao, W., Lee, A.J.T., Liu, Y., Chang, T., Lin, H.: A data mining approach to face detection. Pattern Recognition 43, 1039–1049 (2010)zbMATHCrossRefGoogle Scholar
  13. 13.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. CVPR, pp. 511–518 (2001)Google Scholar
  14. 14.
    Wu, Y., Ai, X.: Face detection in color images using AdaBoost algorithm based on skin color information. In: Proc. Int. Workshop on Knowledge Discovery Data Mining, pp. 339–342 (2004)Google Scholar
  15. 15.
    Wu, J., Brubaker, S.C., Mullin, M.D., Rehg, J.M.: Fast asymmetric learning for cascade face detection. IEEE Trans. Pattern Analysis and Machine Intelligence 30, 369–382 (2008)CrossRefGoogle Scholar
  16. 16.
  17. 17.
    Zhu, Z., Ji, Q.: Robust real-time eye detection and tracking under variable lighting conditions and various face orientations. J. Computer Vision Image Understanding 98, 124–154 (2005)CrossRefGoogle Scholar
  18. 18.
    Zhang, X., Gao, Y.: Face recognition across pose: A review. Pattern Recognition 42, 2876–2896 (2009)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Mahdi Rezaei
    • 1
  • Reinhard Klette
    • 1
  1. 1.The .enpeda.. ProjectThe University of AucklandNew Zealand

Personalised recommendations