Intelligent Face Recognition: Local Versus Global Pattern Averaging

  • Adnan Khashman
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4304)


Face recognition has lately attracted more research aimed at developing intelligent machine recognition which uses information within the encoded facial patterns to learn and recognize the objects. This paper investigates the efficiency of using Global and Local pattern averaging for facial data encoding prior to training a neural network using the averaged patterns. Averaging is a simple but efficient method that creates "fuzzy" patterns as compared to multiple "crisp" patterns, which provide the neural network with meaningful learning while reducing computational expense. A real-life application will be presented throughout recognizing the faces of 60 persons using our database and the ORL face database. Experimental results suggest that using pattern averaging; globally or locally, performs well as part of a fast and efficient intelligent face recognition system.


Neural Network Face Recognition Recognition Rate Face Image Local Average 
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.
    Zhang, B., Zhang, H., Ge, S.: Face recognition by applying wavelet subband representation and kernel associative memory. IEEE Transactions on Neural Networks 15, 166–177 (2004)CrossRefGoogle Scholar
  2. 2.
    Fan, X., Verma, B.: A Comparative Experimental Analysis of Separate and Combined Facial Features for GA-ANN based Technique. In: Proceedings of International Conference on Computational Intelligence and Multimedia Applications, pp. 279–284 (2005)Google Scholar
  3. 3.
    Khashman, A.: Face Recognition Using Neural Networks and Pattern Averaging. In: Wang, J., Yi, Z., Żurada, J.M., Lu, B.-L., Yin, H. (eds.) ISNN 2006. LNCS, vol. 3972, pp. 98–103. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  4. 4.
    Khashman, A., Garad, A.: Intelligent Face Recognition Using Feature Averaging. In: Mehrotra, S., Zeng, D.D., Chen, H., Thuraisingham, B., Wang, F.-Y. (eds.) ISI 2006. LNCS, vol. 3975, pp. 432–439. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  5. 5.
    Turk, M., Pentland, A.P.: Face Recognition Using Eigenfaces. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586–591 (1991)Google Scholar
  6. 6.
    Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection. IEEE Trans. PAMI 19(7), 711–720 (1997)Google Scholar
  7. 7.
    He, X., Yan, S., Hu, Y., Niyogi, P., Zhang, H.J.: Face Recognition Using Laplacianfaces. IEEE Trans. PAMI 27(3), 328–340 (2005)Google Scholar
  8. 8.
    Cambridge University, Olivetti Research Laboratory face database,

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Adnan Khashman
    • 1
  1. 1.Department of Electrical & Electronic EngineeringNear East UniversityLefkosaTurkey

Personalised recommendations