Combined Supervised / Unsupervised Algorithm for Skin Detection: A Preliminary Phase for Face Detection

  • Eyal Braunstain
  • Isak Gath
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8156)


Skin detection in color images is of great importance for the computer vision research community. Many existing skin detection algorithms are characterized by high false detection rates. The proposed algorithm performs offline learning of skin color, but also of "false-skin colors", which may be misclassified as skin using regular histogram or Gaussian skin color models. This supervised learning of false-skin colors produces a significant reduction in false detection rates. Our aim is to extract skin blobs that are suspected to contain faces, which are usually ellipsoid-shaped.

Thus, to extract these blobs, an unsupervised optimal fuzzy clustering (UOFC) algorithm is applied in the spatial image space. Blobs segmented by the clustering procedure are then examined by specific features, e.g. geometrical, to classify them as face candidates.

Sample runs of the algorithm on a bank of images show high skin detection rates with reduced false detection rates.


Skin Detection Supervised Learning Unsupervised Learning Optimal Fuzzy Clustering Likelihood Estimation 


  1. 1.
    Saber, E., Murat Tekalp, A., Eschbach, R., Knox, K.: Automatic Image Annotation Using Adaptive Color Classification. Graphical Models and Image Processing 58(2), 115–126 (1996)CrossRefGoogle Scholar
  2. 2.
    Gath, I., Geva, A.B.: Unsupervised Optimal Fuzzy Clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence 11(7) (1989)Google Scholar
  3. 3.
    Jones, M.J., Rehg, J.M.: Statistical Color Models with Application to Skin Detection. International Journal of Computer Vision 46(1), 81–96 (2002)CrossRefzbMATHGoogle Scholar
  4. 4.
    Forsyth, D.A., Fleck, M., Bregler, C.: Finding naked people. In: Buxton, B.F., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1065, Springer, Heidelberg (1996)Google Scholar
  5. 5.
    Schiele, B., Waibel, A.: Gaze tracking based on face-color. In: Proceedings of the International Workshop on Automatic Face- and Gesture-Recognition, Zurich, Switzerland, pp. 344–349 (1995)Google Scholar
  6. 6.
    Terrillon, J.-C., David, M., Akamatsu, S.: Automatic Detection of Human Faces in Natural Scene Images by Use of a Skin Color Model and of Invariant Moments. In: Proceedings of Third IEEE International Conference on Automatic Face and Gesture Recognition FG (1998)Google Scholar
  7. 7.
    Cai, J., Goshtasby, A.: Detecting human faces in color images. Image and Vision Computing 18, 63–75 (1999)CrossRefGoogle Scholar
  8. 8.
    Bezdek, J.C.: Pattern Recognition with Fuzzy Objective Function Algorithms, New York, Plenum (1981)Google Scholar
  9. 9.
    Bezdek, J.C.: Fuzzy Mathematics in Pattern Classification. Ph.D. dissertation, Cornell Univ., NY (1973)Google Scholar
  10. 10.
    Terrillon, J.-C., Akamatsu, S.: Comparative Performance of Different Chrominance Spaces for Color Segmentation and Detection of Human Faces in Complex Scene Images. Vision Interface, Trois-Rivières, Canada (1999)Google Scholar
  11. 11.
    Vezhnevets, V., Sazonov, V., Andreeva, A.: A Survey on Pixel-Based Skin Color Detection Techniques. In: Proc. Graphicon (2003)Google Scholar
  12. 12.
  13. 13.
    Jedynak, B., Zheng, H., Daoudi, M., Barret, D.: Maximum entropy models for skin detection. Tech. report, Universite des Sciences et Technologies de Lille, France (2002)Google Scholar
  14. 14.
    Wu, Y.-W., Ai, X.-Y.: Face Detection in Color Images Using AdaBoost Algorithm Based on Skin Color Information. Knowledge Discovery and Data Mining (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Eyal Braunstain
    • 1
  • Isak Gath
    • 1
  1. 1.Department of Biomedical EngineeringTechnion - Israel Institute of TechnologyHaifaIsrael

Personalised recommendations