Machine Vision and Applications

, Volume 27, Issue 6, pp 877–891 | Cite as

OptiFuzz: a robust illumination invariant face recognition system and its implementation

  • Bima Sena Bayu DewantaraEmail author
  • Jun Miura
Original Paper


Vision-based human face detection and recognition are widely used and have been shown to be effective in normal illumination conditions. Under severe illumination conditions, however, it is very challenging. In this paper, we address the effect of illumination on the face detection and the face recognition problem by introducing a novel illumination invariant method, called OptiFuzz. It is an optimized fuzzy-based illumination invariant method to solve the effect of illumination for photometric-based human face recognition. The rule of the Fuzzy Inference System is optimized by using a genetic algorithm. The Fuzzy’s output controls an illumination invariant model that is extended from Land’s reflectance model. We test our method by using Yale B Extended and CAS-PEAL face databases to represent the offline experiments, and several videos are recorded at our campus to represent the online indoor and outdoor experiments. Viola–Jones face detector and mutual subspace method are employed to handle the online face detection and face recognition experiments. Based on the experimental results, we can show that our algorithm outperforms the existing and the state-of-the-art methods in recognizing a specific person under variable lighting conditions with a significantly improved computation time. Other than that, using illumination invariant images is also effective in improving the face detection performance.


Illumination invariant Optimized fuzzy Fuzzy Inference System Illumination ratio Illumination invariant model 



We would like to thank to the Directorate General of Higher Education, Ministry of Research, Technology, and Higher Education of Indonesia for financially supporting the first author under Grant No. 224/E4.4/K/2012. This work is also in part supported by JSPS Kakenhi No. 25280093.

Supplementary material

Supplementary material 1 (wmv 25033 KB)


  1. 1.
    Xie, X., Lam, K.M.: Face recognition under varying illumination based on a 2-D face shape model. Pattern Recogn. 38(2), 221–230 (2005)CrossRefGoogle Scholar
  2. 2.
    Gross, R., Brajovie, V.: An image pre-processing algorithm for illumination invariant face recognition. In: 4th International Conference on Audio and Video Based Biometric Person Authentication, pp. 10-18 (2003)Google Scholar
  3. 3.
    Nam, G.P., Park, K.R.: New fuzzy-based retinex method for the illumination normalization of face recognition. Int. J. Adv. Robot. Syst. 9, 103 (2012)Google Scholar
  4. 4.
    Wang, H., Li, S.Z., Wang, Y., Zhang, J.: Self quotient image for face recognition. Int. Conf. Image Process. 2, 1397–1400 (2004)Google Scholar
  5. 5.
    Nishiyama, M., Kozakaya, T., Yamaguchi, O.: Illumination Normalization using Quotient Image-based Techniques, Recent Advances in Face Recognition, pp. 97–108 (2008)Google Scholar
  6. 6.
    Park, Y.K., Park, S.L., Kim, J.K.: Retinex method based on adaptive smoothing for illumination invariant face recognition. Sig. Process. 88, 1929–1945 (2008)CrossRefzbMATHGoogle Scholar
  7. 7.
    Perez, C.A., Castillo, L.E.: Illumination compensation for face recognition based on genetic optimization of the self-quotient image method. In: International Symposium on Optomechatronic Technologies, pp. 322–327 (2009)Google Scholar
  8. 8.
    Chen, W., Er, M.J., Wu, S.: Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain. IEEE Trans. Syst. Man Cybern. 36(2), 458–466 (2006)CrossRefGoogle Scholar
  9. 9.
    Kim, W., Suh, S., Hwang, W., Han, J.J.: SVD face: illumination-invariant face representation. IEEE Signal Process. Lett. 21(11), 1336–1341 (2014)CrossRefGoogle Scholar
  10. 10.
    Luo, Y., Guan, Y.P., Zhang, C.Q.: A Robust Illumination Normalization Method Based on Mean Estimation for Face Recognition. ISRN Machine Vision, pp. 1–10 (2013)Google Scholar
  11. 11.
    Zhang, T., Tang, Y.Y., Fang, B., Shang, Z., Liu, X.: Face recognition under varying illumination using gradientfaces. IEEE Trans. Image Process. 18(11), 2599–2606 (2009)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Ju, Y.A., Soo, H.J., Kim, N.C., Kim, M.H.: Face Recognition Using Local Statistic of Gradients and Correlations. In: 18th EUSIPCO, pp. 1169–1173 (2010)Google Scholar
  13. 13.
    Rui, T., Yang, Z., Liu, F., Jiang, S., Li, H.: Block-based face recognition using WLD. PCM 2013, 811–822 (2013)Google Scholar
  14. 14.
    Ahonen, T., Hadid, A., Pietikainen, M.: Face recognition with local binary patterns. ECCV 2004, 469–481 (2004)zbMATHGoogle Scholar
  15. 15.
    Zhu, J.Y., Zheng, W.S., Lai, J.H.: Logarithm gradient histogram: a general illumination invariant descriptor for face recognition. In: The 10th IEEE International Conference and Workshop on Automatic Face and Gesture Recognition, pp. 1-8 (2013)Google Scholar
  16. 16.
    Mamdani, E.H.: Application of fuzzy logic to approximate reasoning using linguistic synthesis. IEEE Trans. Comput. C 26(12), 1182–1191 (1977)CrossRefzbMATHGoogle Scholar
  17. 17.
    Holland, J.H.: Genetic Algorithms, pp. 66–72. Scientific American, New York (1992)Google Scholar
  18. 18.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Conference on Computer Vision and Pattern Recognition (2001)Google Scholar
  19. 19.
    Guo, R., Dai, Q., Hoeim, D.: Single-image shadow detection and removal using paired regions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2033–2040 (2011)Google Scholar
  20. 20.
    Land, E.: Recent advances in retinex theory. Vision. Res. 26(1), 7–21 (1986)CrossRefGoogle Scholar
  21. 21.
    Peer, P., Solina, F.: An automatic human face detection method. In: Proceedings of the 4th Computer Vision Winter Workshop, pp.122–130 (1999)Google Scholar
  22. 22.
    Elgammal, A., Muang, C., Hu, D.: Skin Detection - A Short Tutorial. Encyclopedia of Biometrics. Springer, Berlin (2009)Google Scholar
  23. 23.
    Grove, G., Zerweck, C., Damia, J.: Human skin coloration using the RGB color space model. In: The 4th International Symposium of L’Oreal Institute for Ethnic Hair and Skin Research (2007)Google Scholar
  24. 24.
    Dewantara, B.S.B., Miura, J.: Fuzzy-based illumination normalization for face recognition. In: IEEE Workshop on Advanced Robotics and Its Social Impacts, pp. 131–136 (2013)Google Scholar
  25. 25.
    Georghiades, A.S., Belhumeur, P.N., Kriegman, D.J.: 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
  26. 26.
    Nanaa, K., Rizon, M., Rahman, M.N.A., Almejrad, A., Aziz, A.Z.A., Mohamed, S.B.: Eye detection using composite cross-correlation. Am. J. Appl. Sci. 10(11), 1448–1456 (2013)CrossRefGoogle Scholar
  27. 27.
    Fukui, K., Yamaguchi, O.: Face recognition using multi-viewpoint patterns for robot vision. In: 11th International Symposium of Robotics Research, pp. 192–201 (2003)Google Scholar
  28. 28.
    Gao, W., Cao, B., Shan, S., Chen, X., Zhou, D., Zhang, X., Zhao, D.: The CAS-PEAL large-scale chinese face database and baseline evaluations. IEEE Trans. Syst. Man Cybern. Part A Syst. Humans 38(1), 149–161 (2008)CrossRefGoogle Scholar
  29. 29.
    Turk, M.A., Pentland, A.P.: Eigenfaces for recognition. J. Cogn. Neurosci. 3, 71–86 (1991)CrossRefGoogle Scholar
  30. 30.
    Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(27), 1–27 (2011)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  1. 1.Toyohashi University of TechnologyToyohashiJapan

Personalised recommendations