STATISCAL-BASED SKIN CLASSIFIER FOR OMNI-DIRECTIONAL IMAGES

Asaf Shupo, Bill Kapralos, Miguel Vargas Martin

Abstract

This paper describes the development of a simple, video-based system capable of efficiently detecting human skin in images captured with an omni-directional video sensor. The video sensor is used to provide a view of the entire visual hemisphere thereby providing multiple dynamic views of a scene. Color models of both skin and non-skin were constructed with images obtained with the omni-directional video sensor. Using a stochastic weak estimator coupled with a linear classifier, the system is capable of distinguishing omni-directional images that contain human skin from those that do not. Results indicate that the system is able to accomplish this task in a simple and computationally efficient manner. The ability to obtain an image of the entire scene from a single viewpoint using the omni-directional video sensor and determine whether the image contains human skin (e.g., one or more humans) in a simple and efficient manner is practical as a precursor for a number of applications including teleconferencing, remote learning, and video surveillance, the application of interest in this work.

References

  1. Baker, S. and Nayar, S. (1999). A theory of single viewpoint catadioptric image formation. International Journal of Computer Vision, 35(2):1-22.
  2. Basu, A. and Southwell, D. (1995). Omni-directional sensors for pipe inspection. In IEEE Transactions on Systems Man and Cybernetics, volume 25, pages 3107- 3112.
  3. Boult, T., Michaels, R., Gao, P., Lewis, C., Yin, W., and Erkan, A. (1998). Frame rate omni-directional surveillance and tracking of camouflaged and occluded targets.
  4. Bradski, G. (1998). Computer vision face tracking for use in a perceptual user interface. Technical report, Intel Corp., Santa Clara, CA USA.
  5. Chai, D. and Ngan, K. (1999). Face segmentation using skin-color map in videophone applications. IEEE Transactions on Circuits Systems and Video Technology, 9(4):551-564.
  6. Chopra, M., Vargas Martin, M., Rueda, L., and Hung, P. (2006). A source address reputation system to combating child pornography at the network level. In Proceedings of the IADIS International Conference on Applied Computing, San Sebastian, Spain.
  7. Duda, R. O., Hart, P. E., and Stork, D. E. (2000). Pattern Classification. Wiley Interscience, Hoboken, NJ. USA, second edition.
  8. Gutchess, D., Jain, A., and Cheng, S. (2000). Automatic surveillance using omni-directional and active cameras. In Proceedings of the 2000 Asian Conference on Computer Vision.
  9. Hans, S., Anderson, H., and Granum, E. (1999). Skin color detection under changing lighting conditions. In Proceedings of the 7th Symposium on Intelligent Robotics Systems,, pages 187-195, Columbia, Portugal.
  10. Herpers, R., Derpanis, K., Topalovic, D., and Tsotsos, J. (1999). Detection and tracking of faces in real environments. In Proceedings of the International Workshop on Recognition, Analysis and Tracking of Faces in Real-Time Systems , pages 96-104, Korfu, Greece.
  11. Jones, M. and Rehg, J. (1998). Statistical color models with applications to skin detection. Technical Report CRL 98/11, Compaq Computer Corp., Cambridge, MA USA.
  12. Kapralos, B., Jenkin, M., and Milios, E. (2003). Audiovisual localization of multiple speakers in a video teleconferencing setting. Journal of Imaging Science and Technology, 13(1):95-105.
  13. Nayar, S. (1997). Omnidirectional video camera. In Proceedings of the DARPA Image Understanding Workshop, pages 235-241, New Orleans, LA.
  14. Oommen, B. J. and Rueda, L. (2005). On utilizing stochastic learning weak estimators for training and classification of patterns with non-stationary distributions. In Proc. 28th German Conf. on AI, pages 107-120, Koblenz, Germany.
  15. Oommen, B. J. and Rueda, L. (2006). On utilizing stochastic learning weak estimators for training and classification of patterns with non-stationary distributions. Journal of Pattern Recognition, 39:328-341.
  16. Peri, V. and Nayar, S. (1997). Generation of perspective and panoramic video from omnidirectional video. In Proceedings of the DARPA Image Understanding Workshop, pages 243-245, New Orleans, LA USA.
  17. Raja, Y., McKenna, J., and Gong, S. (1998). Segmentation and tracking using color mixture models. In Proceedings of the Third Asian Conference of Computer Vision.
  18. Shupo, A., Vargas Martin, M., Rueda, L., Bulkan, A., Chen, Y., and Hung, P. (2006). Toward efficient detection of child pornography in the network infrastructure. IADIS International Journal on Computer Science and Information Systems, 1(2):15-31.
  19. Stiefelhagen, R., Yang, J., and Waibel, A. (1999). Modeling focus of attention for meeting indexing. In Proceedings of the ACM Multemedia 7899, pages 3-10, Orlando, FL USA.
  20. Swain, M. and Ballard, D. (1991). Color indexing. International Journal of Computer Vision, 7:11-32.
  21. Yang, J. and Waibel, A. (1996). A real time face tracker. In Proceedings of the 3rd IEEE Workshop on Applications of Computer Vision, Sarasota, FL, USA.
  22. Yasushi, Y. (1999). Omni-directional sensing and its applications. IEEE Transactions on Information and Systems, E82-3.
  23. Yong, R., Gupta, A., and Cadiz, J. (2001). Viewing meetings captured by an omni-directional camera. In ACM Transactions on Computer-Human Interaction .
  24. Zheng, J. and Tsuji, S. (1992). Panoramic representation for route recognition by a mobile robot. International Journal of Computer Vision, 9(1):55-76.
Download


Paper Citation


in Harvard Style

Shupo A., Kapralos B. and Vargas Martin M. (2007). STATISCAL-BASED SKIN CLASSIFIER FOR OMNI-DIRECTIONAL IMAGES . In Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 3: Human Presence Detection for Context-aware Systems, (VISAPP 2007) ISBN 978-972-8865-75-7, pages 11-17. DOI: 10.5220/0002060800110017


in Bibtex Style

@conference{human presence detection for context-aware systems07,
author={Asaf Shupo and Bill Kapralos and Miguel Vargas Martin},
title={STATISCAL-BASED SKIN CLASSIFIER FOR OMNI-DIRECTIONAL IMAGES},
booktitle={Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 3: Human Presence Detection for Context-aware Systems, (VISAPP 2007)},
year={2007},
pages={11-17},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002060800110017},
isbn={978-972-8865-75-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 3: Human Presence Detection for Context-aware Systems, (VISAPP 2007)
TI - STATISCAL-BASED SKIN CLASSIFIER FOR OMNI-DIRECTIONAL IMAGES
SN - 978-972-8865-75-7
AU - Shupo A.
AU - Kapralos B.
AU - Vargas Martin M.
PY - 2007
SP - 11
EP - 17
DO - 10.5220/0002060800110017