Human Skin Segmentation in Color Images Using Gaussian Color Model

  • Ravi Subban
  • Richa Mishra
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 235)


Use of color spaces for human skin detection has been efficiently used for the several decades. It also plays an efficient role in face detection, tracking and recognition. This paper presents a comparative evaluation on the performance of skin color pixel classification methods using four rarely used color spaces and three commonly used skin detection methods. The first two skin detection methods used are piecewise linear decision boundary classifier algorithm and Gaussian color model which produce better results for color images with a wide variety of human skin tones. The third method deals with the Gaussian model with combination of two color spaces. All the results are experimentally evaluated with the help of few commonly used face databases.


Color space Combination of two color spaces Gaussian model Linear decision boundary classifier Skin detection 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Shin, M.C., Chang, K.I., Tsap, L.V.: Does Colorspace Transformation Make Any Difference on Skin Detection. In: Proceedings of the Sixth IEEE Workshop on Applications of Computer Vision, WACV 2002 (2002)Google Scholar
  2. 2.
    Hsieh, C.-C., Liou, D.-H., Lai, W.-R.: Enhanced Face-Based Adaptive Skin Color Model. Journal of Applied Science and Engineering 15(2), 167–176 (2012)Google Scholar
  3. 3.
    Boussaid, F., Chai, D., Bouzerdoum, A.: On-Chip Skin Detection for Color CMOS Imagers. In: Proceedings of the International Conference on MEMS, NANO and Smart Systems, ICMENS 2003 (2003)Google Scholar
  4. 4.
    Yang, Y., Wang, Z., Zhang, M., Yang, Y., Beijing, N.: Skin Region Tracking using Hybrid Color Model and Gradient vector Flow. Proceedings of the IEEE (2010)Google Scholar
  5. 5.
    Sahdra, G.S., Kailey, K.S.: Detection of Contaminants in Cotton by using YDbDr color space. Int. J. Computer Technology & Applications 3(3), 1118–1124 (2012)Google Scholar
  6. 6.
    Wang, C.-X., Li, Z.-Y.: Face Detectiion based on Skin Gaussian Model and KL Transform. In: Proceeding of Ninth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing. IEEE (2008)Google Scholar
  7. 7.
    Zarit, B.D., Super, B.J., Quek, F.K.H.: Comparison of Five Color Models in Skin Pixel ClassificationGoogle Scholar
  8. 8.
    Veznevets, V., Sazonov, V., Andreeva, A.: A Survey on Pixel-Based Skin Color Detection Techniques (2002)Google Scholar
  9. 9.
    Phung, S.L., Bouzerdoum, A., Chai, D.: Skin Segmentation Using Color Pixel Classification: Analysis and Comparison. IEEE Transactions on Pattern Analysis and Machine Intelligence 27(1) (January 2005)Google Scholar
  10. 10.
    Pasteau, F., Strauss, C., Babel, M., Deforge, O., Bedat, L.: Improved Colour Decorrelation for Lossless Colour Image Compression using the LAR Codec. In: European Signal Processing Conference, EUSIPCO 2009. Royaume-Uni, Glasgow (2009)Google Scholar
  11. 11.
    Ravi Subban, S., Mishra, R.: Face Detection in Color Images Based on Explicitly-Defined Skin Color Model. CCIS, vol. 361. Springer (2012)Google Scholar
  12. 12.
    Ibrahim, N.B., Selim, M.M., Zayed, H.H.: A Dynamic Skin Detector Based on Face Skin Tone Color. In: 8th International Conference on Informatics and Systems (INFOS 2012), May 14-16 (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Ravi Subban
    • 1
  • Richa Mishra
    • 1
  1. 1.Department of Computer SciencePondicherry UniversityPuducherryIndia

Personalised recommendations