Automatic Detection of Facial Landmarks in Images with Different Sources of Variations

  • Ángel Sánchez
  • A. Belén Moreno
  • José F. Vélez
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7931)


Accurate and robust extraction of feature points in 2D facial images has multiple applications in biometric face recognition, facial expression classification, facial animation or human-computer interaction, among others. This paper describes a methodology for the fully automatic identification of 20 relevant facial points on static gray level images containing different types of variations. To solve the problem considered, we mainly use the shape and texture information provided by the images. The main advantage of this approach is its precision at point location, even for images with pronounced expressions. The presented method is tolerant to moderate scale changes and pose variations, and also to different illumination conditions. Our approach was tested on two of the most common databases used for facial expression analysis: Cohn-Kanade and JAFFE datasets, achieving respective average correct point detection rates of 94.2% and 96.15% on them. Our results were also compared to other related results presented in the literature on the same databases.


Facial landmark detection face region location facial expressions anthropometric measurements pattern recognition 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Arca, S., Campadelli, P., Lanzarotti, R.: A face recognition system bases on automatically determined facial fiducial points. Pattern Recognition 39, 432–443 (2006)zbMATHCrossRefGoogle Scholar
  2. 2.
    Bagherian, E., Rahmat, R.W., Udzir, N.I.: Extraction of Facial Feature Points. International Journal of Computer Science and Network Security 9, 49–53 (2009)Google Scholar
  3. 3.
    Campadelli, P., Lanzarotti, R.: Fiducial point localization in color images of face foregrounds. Image and Vision Computing 22, 863–872 (2004)CrossRefGoogle Scholar
  4. 4.
    Farkas, L.G.: Anthropometry of the Head and Face. L. Williams and Wilkins (1994)Google Scholar
  5. 5.
    Gizatdinova, Y., Surakka, V.: Feature-based detection of facial landmarks from neutral and expressive facial images. IEEE Trans. PAMI 28, 135–139 (2006)CrossRefGoogle Scholar
  6. 6.
    Kanade, T., Cohn, J.F., Tian, Y.: Comprehensive Database for Facial Expression Analysis. In: Proc. IEEE Intl. Conf. on Automatic Face and Gesture Recognition (FG 2000), pp. 46–53 (2000)Google Scholar
  7. 7.
    Lai, J.H., et al.: Robust Facial Feature Point Detection Under Nonlinear Illuminations. In: Proc. IEEE ICCV, pp. 168–174 (2001)Google Scholar
  8. 8.
    Lyons, J., et al.: Coding Facial Expressions with Gabor Wavelets. In: Proc. IEEE Intl. Conf. on Automatic Face and Gesture Recognition, pp. 200–205 (1998)Google Scholar
  9. 9.
    Sayeed, A., et al.: Detection of Facial Feature Points using Anthropometric Face Model. In: Signal Proc. for Image Enhancement and Multimedia Proc., pp. 189–200. Springer (2008)Google Scholar
  10. 10.
    Szeliski, R.: Computer Vision: Algorithms and Applications. Springer (2011)Google Scholar
  11. 11.
    Viola, P., Jones, M.: Rapid Object Detection using a Boosted Cascade of Simple Features. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 511–518 (2001)Google Scholar
  12. 12.
    Vukadinovic, D., Pantic, M.: Fully Automatic Facial Feature Point Detection using Gabor Feature Boosted Classifiers. In: Proc. IEEE SMC Conf., pp. 1692–1698 (2005)Google Scholar
  13. 13.
    Zhou, Z.-H., Geng, X.: Projection functions for eye detection. Pattern Recognition 37, 1049–1056 (2004)zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Ángel Sánchez
    • 1
  • A. Belén Moreno
    • 1
  • José F. Vélez
    • 1
  1. 1.Departamento de Ciencias de la ComputaciónUniversidad Rey Juan CarlosMóstolesSpain

Personalised recommendations