MQI Based Face Recognition Under Uneven Illumination

  • Yaoyao Zhang
  • Jie Tian
  • Xiaoguang He
  • Xin Yang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4642)


Face recognition has been applied in many fields, while face recognition under uneven illumination is still an open problem. Our approach is based on Morphological Quotient Image (MQI) for illumination normalization, and Dynamic Morphological Quotient Image (DMQI) is proposed to improve the performance. Before applying MQI, singularity noise should be removed, and after MQI operation, an effective scheme is used to wipe off the grainy noise as postprocessing. Weighted normalized correlation is adopted to measure the similarity between two images. Experiments on Yale Face Database B show that the proposed MQI method has a good performance of face recognition under various light conditions. Moreover, its computational cost is very low.


face recognition illumination normalization quotient image morphological operation 


  1. 1.
    Zhao, W., Chellappa, R., Rosenfeld, A., Phillips, P.: Face recognition: A literature survey. UMD CfAR Technical Report, CAR-TR-948 (2000)Google Scholar
  2. 2.
    Shashua, A., Riklin-Raviv, T.: The quotient image: Classbased re-rendering and recognition with varying illuminations. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(2), 129–139 (2001)CrossRefGoogle Scholar
  3. 3.
    Shan, S., Gao, W., Cao, B., Zhao, D.: Illumination normalization for robust face recognition against varying lighting conditions. In: Proc. of IEEE Workshop on AMFG, pp. 157–164. IEEE Computer Society Press, Los Alamitos (2003)Google Scholar
  4. 4.
    Wang, H., Li, S.Z., Wang, Y.: Generalized quotient image. In: IEEE International Conference on Computer Vision and Pattern Recognition, IEEE Computer Society Press, Los Alamitos (2004)Google Scholar
  5. 5.
    Chen, T., Yin, W., Zhou, X., Comaniciu, D., Huang, T.: Illumination Normalization for Face Recognition and Uneven Background Correction Using Total Variation Based Image Models. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 532–539 (2005)Google Scholar
  6. 6.
    He, X., Jie, T., Wu, L., Zhang, Y., Yang, X.: Illumination Normalization with Morphological Quotient Image. Journal of Software 18(9) (2007)Google Scholar
  7. 7.
    Gross, R., Brajovie, V.: An Image Preprocessing Algorithm for Illumination Invariant Face Recognition. In: Kittler, J., Nixon, M.S. (eds.) AVBPA 2003. LNCS, vol. 2688, pp. 10–18. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  8. 8.
    Georghiades, A., Belhumeur, P., Kriegman, D.: From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose. IEEE Trans. on Pattern Analysis and Machine Intelligence 23(6), 630–660 (2001)CrossRefGoogle Scholar
  9. 9.
    Georghiades, A., Kriegman, D., Belhumeur, P.: Illumination Cones for Recognition under Variable Lighting: Faces. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society Press, Los Alamitos (1998)Google Scholar
  10. 10.
    He, X., Tian, J., He, Y., Yang, X.: Face Recognition with Relative Difference Space and SVM. In: Proce. of the 18th International Conference of Pattern Recognition, HongKong (August 2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Yaoyao Zhang
    • 1
  • Jie Tian
    • 1
  • Xiaoguang He
    • 1
  • Xin Yang
    • 1
  1. 1.Center for Biometrics and Security Research, Key Laboratory of Complex Systems and Intelligence Science, Institute of Automation, Chinese Academy of Sciences, P.O. Box 2728, Beijing, 100080, Email:tian@ieee.orgP.R.China

Personalised recommendations