Advertisement

A Comparative Study of the Objectionable Video Classification Approaches Using Single and Group Frame Features

  • Seungmin Lee
  • Hogyun Lee
  • Taekyong Nam
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4132)

Abstract

This paper deals with the methods for classifying whether a video is harmful or not and also evaluates their performance. The objectionable video classification can be performed using two methods. One can be practiced by judging whether each frame included in the video is harmful, and the other be obtained by using the features reflecting the entire characteristics of the video. The former is a single frame-based feature and the latter is a group frame-based feature. Experimental results show that the group frame-based feature outperforms the single frame-based feature and is robust to the objectionable video classification.

Keywords

Support Vector Machine Face Detection Objectionable Video Color Descriptor Support Vector Machine Learning 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Fleck, M., Forsyth, D., Bregler, C.: Finding Naked People. In: European Conf. on Computer Vision, vol. 2, pp. 592–602 (1996)Google Scholar
  2. 2.
    Jones, M.J., Regh, J.M.: Statistical Color Model with Application to Skin Detection. Technical Report CRL (1998)Google Scholar
  3. 3.
    Wang, J.Z., Wiederhold, G., Firschein, O.: System for Screening Objectionable Imagers. Computer Communications 21, 1355–1600 (1998)CrossRefGoogle Scholar
  4. 4.
    Bosson, A., Cawley, G.C., Chan, Y., Harvey, R.: Non-Retrieval: Blocking Pornographic Images. In: International Conf. on Image and Video Retrieval (2002)Google Scholar
  5. 5.
    Lee, J.-H.: Automatic Video Management System Using Face Recognition and MPEG-7 Visual Descriptors. ETRI Journal 27, 806–809 (2005)CrossRefGoogle Scholar
  6. 6.
    Jeong, C.-Y., Kim, J.-S., Hong, K.-S.: Appearance-Based Nude Image Detection. In: ICPR, pp. 467–470 (2004)Google Scholar
  7. 7.
    Tsishkou, D., Hammami, M., Chen, L.: Face Detection in Video Using Combined Data-mining and Histogram based Skin-color Model. In: Proceedings of 3rd International Symposium on Image and Signal Processing and Analysis, pp. 500–503 (2003)Google Scholar
  8. 8.
    Ikeda, O.: Segmentation of Face in Video Footage Using HSV Color for Face Detection and Image Retrieval. In: Image Processing, ICIP 2003, Proceedings, vol. 3, pp. 14–17 (2003)Google Scholar
  9. 9.
    Manjunath, B.S., Salembier, P., Sikora, T.: Introduction to MPEG-7. John Wiley & Sons, Ltd., Chichester (2002)Google Scholar
  10. 10.
    Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)MATHGoogle Scholar
  11. 11.
    Joachims, T.: SVMlight Support Vector Machine, http://svmlight.joachims.org/

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Seungmin Lee
    • 1
  • Hogyun Lee
    • 1
  • Taekyong Nam
    • 1
  1. 1.Electronics and Telecommunications Research Institute (ETRI)DaejeonSouth Korea

Personalised recommendations