Robust Face Recognition of Images Captured by Different Devices

  • Guangda Su
  • Yan Shang
  • Baixing Zhang
Part of the Lecture Notes in Control and Information Sciences book series (LNCIS, volume 345)


The performance of a face recognition system is greatly influenced when the target and test images are captured through different imaging devices, like scanned photos, images captured through digital camera or video camera. By excluding the influence of lighting, expression, as well as time difference, the difference of gray scale distribution of images captured through different devices is analyzed in this paper. Based on this analysis, we decomposed the facial feature into general feature and local feature. General facial feature is determined by the imaging device and local facial feature represents the individual facial difference, which is to be used for face recognition. Before performing face recognition, the general facial feature is excluded through gray scale normalization. In this paper the normalization was carried out through gray scale sorting, and the experiment results under ideal and realistic conditions showed the performance improvement of face recognition system through this technique.


Face Recognition Recognition Rate Facial Image Gray Scale Facial Feature 
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.
    Su, G.D., Zhang, C.P., Ding, R., Du, C.: MMP-PCA Face Recognition Method. Electronic Letters, Vol. 38, No. 25, (2002) 415–438CrossRefGoogle Scholar
  2. 2.
    Ding, R., Su, G.D., Lin, X.G.: Face Recognition Algorithm Using Both Local Information and Global Information. Electronic Letters, Vol. 38, No. 8, (2002) 363–364CrossRefGoogle Scholar
  3. 3.
    Zhao, W., Chellappa, R., Phillips, J., Rosenfeld, A.: Face Recognition: A Literature Survey. ACM Computing Surveys, (2003) 399–458Google Scholar
  4. 4.
    Turk, M., Pentland, A.:Face Recognition Using Eigenfaces. Proc. IEEE CVPR’ 91, (1991) 586–591Google Scholar
  5. 5.
    Pentland, A., Moghaddam, B., Starner, T.: View-Based and Modular Eigenspaces for Face Recognition. Proc. IEEE CVPR’ 94, (1994) 84–91Google Scholar
  6. 6.
    Zhang, B.X., Su, G.D.: Research on Characteristic of Facial Imaging and Goals of Facial Image Normalization. Optic Electronic · Laser, Vol. 14, No. 4, (2003) 406–410Google Scholar
  7. 7.
    Hezeltine, T.: Evaluation of Image Pre-processing Techniques for Eigenface Based Face Recognition. the Second International Conference on Image and Graphics (ICIG2002), Hefei, China, SPIE, Vol. 4875, (2002) 677–685Google Scholar
  8. 8.
    Gross, R., Baker, S., Matthews, I., Kanade, T.: Face Recognition Across Pose and Illumination. In: Li, S.Z., Jain, Anil K. (eds.): Handbook of Face Recognition. Springer-Verlag, June, 2004Google Scholar
  9. 9.
    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 Transactions on Pattern Analysis and Machine Intelligence, Vol. 23, No. 6, (2001) 643–660CrossRefGoogle Scholar
  10. 10.
    Tian, Y.L., Kanade, T., Cohn, J.F.: Recognizing Action Units for Facial Expression Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 23, No. 2, (2001) 97–115CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Guangda Su
    • 1
  • Yan Shang
    • 1
  • Baixing Zhang
    • 1
  1. 1.Research Institute of Image and Graphics Electronic Engineering DepartmentTsinghua UniversityBeijingP.R. China

Personalised recommendations