Illumination Invariant Face Alignment Using Multi-band Active Appearance Model

  • Fatih Kahraman
  • Muhittin Gökmen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3776)


In this study, we present a new multi-band image representation for improving AAM segmentation accuracy for illumination invariant face alignment. AAM is known to be very sensitive to the illumination variations. We have shown that edges, originating from object boundaries are far less susceptible to illumination changes. Here, we propose a contour selector which mostly collects contours originating from boundaries of the face components (eyes, nose, chin, etc.) and eliminates the others arising from texture. Rather than representing the image using grey values, we use Hill, Hue and Grey value (HHG) for image representation. We demonstrate that HHG representation gives more accurate and reliable results as compared to image intensity alone under various lighting conditions.


Face Recognition Face Image Object Boundary Illumination Change Illumination Variation 
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.


  1. 1.
    Xiaoguang, L., Hsu, R., Jain, A.K.: Face Recognition with 3D Model-Based Synthesis. In: International Conference on Bioinformatics and its Applications, Florida, USA, pp. 315–333 (2004)Google Scholar
  2. 2.
    Turk, M.A., Pentland, A.P.: Face recognition using eigenfaces. In: IEEE Computer Society Conference Computer Vision and Pattern Recognition, pp. 586–591 (1991)Google Scholar
  3. 3.
    Ezzat, T., Poggio, T.: Facial Analysis and Synthesis Using Image-Based Models. In: International Workshop on AutomaticFace and Gesture Recognition 1996, Killington, Vermont, pp. 116–121 (1996)Google Scholar
  4. 4.
    Ezzat Cootes, T.F., Kittipanyangam, P.: ComparingVariations on the Active Appearance Model Algorithm. In: Proc. BMVC 2002, vol. 2, pp. 837–846 (2002)Google Scholar
  5. 5.
    Nastar, C., Moghaddam, B., Pentland, A.: Generalized Image Matching: Statistical Learning of Physically-Based Deformations. In: Buxton, B.F., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1064, pp. 589–598. Springer, Heidelberg (1996)CrossRefGoogle Scholar
  6. 6.
    Lanitis, A., Taylor, C., Taylor, T.: Automatic Interpretation and Coding of Face Images Using Flexible Models. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(7), 743–756 (1997)CrossRefGoogle Scholar
  7. 7.
    Edwards, G.J., Taylor, C.J., Cootes, T.: Learning to Identify and Track Faces in Image Sequences. In: British Machine Vision Conference 1997, Colchester, UK (1997)Google Scholar
  8. 8.
    Ming, Z., Stan, Z.L., Chun, C.: Subspace analysis and optimization for active appearance model based face alignment. In: The 6th International Conference on Automatic Face and Gesture Recognition, Seoul, Korea (May 2004)Google Scholar
  9. 9.
    Ahlberg, J.: A System for Face Localization and Facial Feature Extraction, Report No. LiTH-ISY-R-2172 (July 1999)Google Scholar
  10. 10.
    Viola, P., Jones, M.J.: Rapid Object Detection using a Boosted Cascade of Simple Features. In: Conference on Computer Vision and Pattern Recognition (2001)Google Scholar
  11. 11.
    Viola, P., Jones, M.J.: Robust real-time object detection. In: ICCV Workshop on Statistical and Computation Theories of Vision (2001)Google Scholar
  12. 12.
    Lienhart, R., Maydt, J.: An Extended Set of Haar-like Features for Rapid Object Detection. In: Proceedings of the ICIP 2002 (2002)Google Scholar
  13. 13.
    Kurt, B., Gökmen, M., Jain, A.K.: Image Compression Based On Centipede Model. In: Proceedings of International Conference on Image Analysis and Processing, ICIAP 1999, vol. I, pp. 303–310 (1997)Google Scholar
  14. 14.
    Gökmen, M., Jain, A.K.: λτ-Space Representation of Images and Generalized Edge Detection. IEEE Trans.on Pattern Analysis and Machine Intelligence 19(6), 545–563 (1997)CrossRefGoogle Scholar
  15. 15.
    Cootes, T., Cooper, D., Taylor, C., Graham, J.: Active shape models - their training and application. Computer Vision and Image Understanding 61(1), 38–59 (1995)CrossRefGoogle Scholar
  16. 16.
    Stegman, M.B.: Analysis and segmentation of face images using point annotations and linear subspace techniques, Technical Report, DTU (2002)Google Scholar
  17. 17.
    Stegmann, M.B., Larsen, R.: Multi-band Modelling of Appearance, Image and Vision Computing, vol. Elsevier Science 21(1), 61–67 (2003)Google Scholar
  18. 18.
    Stegmann, M.B., Ersboll, B.K., Larsen, R.: FAME ”A flexible appearance modeling environment. IEEE Trans. on Medical Imaging 22(10), 1319–1331 (2003)CrossRefGoogle Scholar
  19. 19.
    Yilmaz, A., Gökmen, M.: Eigenhills vs Eigenface and Eigenedge. Pattern Recognition 34, 181–184 (2001)CrossRefGoogle Scholar
  20. 20.
    Cootes, T.F., Taylor, C.J.: On representing edge structure for model matching. In: Proc. IEEE Computer Vision and Pattern Recognition - CVPR, vol. 1, pp. 1114–1119 (2001)Google Scholar
  21. 21.
    Kahraman, F., Kurt, B., Gökmen, M.: Active Appearance Model Based Face Recognition. In: Proc. IEEE 13th Signal Processing And Communications Applications Conference, Kayseri, Turkey, vol. 1, pp. 209–212 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Fatih Kahraman
    • 1
  • Muhittin Gökmen
    • 2
  1. 1.Institute of Informatics, Computer ScienceIstanbul Technical UniversityIstanbulTurkey
  2. 2.Computer Engineering DepartmentIstanbul Technical UniversityIstanbulTurkey

Personalised recommendations