Advertisement

Non-retrieval: Blocking Pornographic Images

  • Alison Bosson
  • Gavin C. Cawley
  • Yi Chan
  • Richard Harvey
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2383)

Abstract

We extend earlier work on detecting pornographic images. Our focus is on the classification stage and we give new results for a variety of classical and modern classifiers. We find the artificial neural network offers a statistically significant improvement. In all cases the error rate is too high unless deployed sensitively so we show how such a system may be built into a commercial environment.

Keywords

Support Vector Machine Receiver Operating Characteristic Curve Colour Space Near Neighbour Multilayer Perceptron 
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. M., Forsyth, D. A., Bregler, C.: Finding naked people. In: European Conference on Computer Vision. Volume II., Springer-Verlag (1996) 593–602Google Scholar
  2. 2.
    Jones, M. J., Rehg, J. M.: Statistical color models with application to skin detection. Technical Report CRL 98/11, Compaq Cambridge Research Laboratory (1998)Google Scholar
  3. 3.
    Wang, J., Wiederhold, G., Firschein, O.: System for screening objectionable images using Daubechies’ wavelets and color histograms. In Stenmetz, R., Wolf, L. C., eds.: Proc. IDMS’97. Volume 1309., Springer-Verlag LNCS (1997) 20–30Google Scholar
  4. 4.
    Chan, Y., Harvey, R., Smith, D.: Building systems to block pornography. In Eakins, J., Harper, D., eds.: Challenge of Image Retrieval, BCS Electronic Workshops in Computing series (1999) 34–40Google Scholar
  5. 5.
    Chan, Y., Harvey, R., Bagham, J.: Using colour features to block dubious images,. In: Proc. Eusipco 2000. (2000)Google Scholar
  6. 6.
    McCullagh, P., Nelder, J. A.: Generalized Linear Models. 2nd edn. Volume 37 of Monographs on Statistics and Applied Probability. Chapman & Hall (1989)Google Scholar
  7. 7.
    Dasarathy, B. V., ed.: Nearest neighbour (NN) norms: NN pattern classification techniques. IEEE Computer Society, Washingtion, DC (1991)Google Scholar
  8. 8.
    Bishop, C. M.: Neural networks for pattern recognition. OUP (1995)Google Scholar
  9. 9.
    Williams, P. M.: Bayesian regularisation and pruning using a Laplace prior. Neural Computation 7 (1995) 117–143CrossRefGoogle Scholar
  10. 10.
    Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines (and other kernel-based learning methods). CUP (2000)Google Scholar
  11. 11.
    Platt, J. C.: Probabilities for SV machines. In Smola, A. J., Bartlett, P. J., Schölkopf, B., Schuurmans, D., eds.: Advances in Large Margin Classifiers. MIT Press, Cambridge, Massachusetts (2000) 61–73Google Scholar
  12. 12.
    Joachims, T.: Estimating the generalization performance of a SVM efficiently. Technical Report LS-8 No. 25, Univerität Dortmund, Fachbereich Informatik (1999)Google Scholar
  13. 13.
    Stone, M.: Cross-validatory choice and assessment of statistical predictions. Journal of the Royal Statistical Society B 36 (1974) 111–147Google Scholar
  14. 14.
    Gillick, L., Cox, S.: Some statistical issues in the comparison of speech recognition algorithms. In: Proceedings, ICASSP. Volume 1. (1989) 532–535Google Scholar
  15. 15.
    Zalzberg, S. L.: On comparing classifiers: pitfalls to avoid and a recommended approach. Data Mining and Knowledge Discovery 1 (1997) 317–327CrossRefGoogle Scholar
  16. 16.
    Bradley, A. P.: The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognition 30 (1997) 1145–1159CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Alison Bosson
    • 1
  • Gavin C. Cawley
    • 2
  • Yi Chan
    • 2
  • Richard Harvey
    • 2
  1. 1.Clearswift CorporationThealeUK
  2. 2.School of Information SystemsUniversity of East AngliaNorwichUK

Personalised recommendations