SVM-Based Pornographic Images Detection

  • Haiming YinEmail author
  • Xiangqiong Huang
  • Yuanwang Wei
Conference paper
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 115)


In this paper, we present a new automatic system for pornographic image detecting. An improved section skin model in RGB color space is employed to identify the rough skin regions. An original texture filter is used to modify these regions. Then the useful information of skin regions is extracted. Close-up face images are excluded by the face detection. At last all the information of skin and face is all fed to the SVM Classifier to tell whether the image is pornographic or not. Our experiments on real-world web image data indicate that our system can improve the accuracy of pornographic content detection significantly.


pornographic image detection skin identifying texture filtering fractal dimension 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Fleck, M.M., Forsyth, D.A., Bregler, C.: Finding Naked People. In: Buxton, B.F., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1065, pp. 593–602. Springer, Heidelberg (1996)Google Scholar
  2. 2.
    Drimbarean, A.F.: Image processing techniques to detect and filter objectionable images based on skin tone and shape recognition. In: Proceedings International Conference on Consumer Electronics, pp. 278–281 (2001)Google Scholar
  3. 3.
    Zheng, H., Liu, H., Daoudi, M.: Blocking objectionable images: adult images and harmful symbols. In: Proceedings of the IEEE International Conference on Multimedia and Expo. (ICME), pp. 1223–1226 (June 2004)Google Scholar
  4. 4.
    Xu, Y., Li, B., Xue, X., Lu, H.: Region-based pornographic image detection. In: IEEE 7th Workshop on Multimedia Signal Processing (MMSP), pp. 1–4 (November 2005)Google Scholar
  5. 5.
    Lee, J.-S., Kuo, Y.-M., Chung, P.-C.: Detecting Nakedness in Color Images. In: Sencar, H.T., Velastin, S., Nikolaidis, N., Lian, S. (eds.) Intelligent Multimedia Analysis for Security Applications. Studies in Computational Intelligence, vol. 282, pp. 225–236. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  6. 6.
    Lee, J.-S., Kuo, Y.-M., Chung, P.-C.: The adult image identification based on online sampling. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN), pp. 2566–2571 (July 2006)Google Scholar
  7. 7.
    Shen, X., Wei, W., Qian, Q.: The filtering of internet images based on detecting erotogenic-part. In: Proceedings of the Third International Conference on Natural Computation (ICNC), pp. 732–736. IEEE Computer Society, Washington, DC, USA (2007)CrossRefGoogle Scholar
  8. 8.
    Sevimli, H., Esen, E., Ateş, T.K., Ozan, E.C.: Adult Image Content Classification Using Global Features and Skin Region Detection. LNEE, vol. 62(1), pp. 253–258 (2010)Google Scholar
  9. 9.
    Jones, M.J., Rehg, J.M.: Statistical color models with application to skin detection. In: Proceedings of Computer Vision and Pattern Recognition, pp. 274–280 (1999)Google Scholar
  10. 10.
    Kovǎc, J., Peer, P., Solina, F.: Human Skin Colour Clustering for Face Detection. In: Proceedings of EUROCON, pp. 144–148 (2003)Google Scholar
  11. 11.
    Mandelbrot, B.B.: The fractal geometry of nature, p. 125. W H Freeman and Company, New York (1983)Google Scholar
  12. 12.
    Cao, L.: Machine recognition of citrus variety based on the fractal dimensions of perimeter-area. Transactions of the CSAE 26(2), 351–355 (2010)Google Scholar
  13. 13.
    Liu, C.: A bayesian discriminating features method for face detection. IEEE Trans. Pattern Analysis and Machine Intelligence 25, 725–740 (2003)CrossRefGoogle Scholar
  14. 14.
    A jörgensen. AdaBoost, Histograms for Fast Face Detection. Master of Science Thesis Stockholm, Sweden (2006)Google Scholar
  15. 15.
    Guo, G., Li, S.Z., Chan, K.L.: Support vector machines for face recognition. Image and Vision Computing 19(9-10), 631–638 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.Computer Application Research LabJiaxing UniversityJiaxingChina

Personalised recommendations