Dynamic Texture Recognition Based on Compression Artifacts

  • Dubravko Ćulibrk
  • Matei Mancas
  • Vladimir Ćrnojevic
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 285)


The paper proposes a novel approach to the classification of compressed videos containing dynamic textures. The term dynamic texture is usually used with reference to image sequences of various natural processes that exhibit stochastic dynamics (e.g., water, fire and windblown vegetation). Description and recognition of dynamic textures have attracted growing attention.

Although one of the most important prospective applications of the technology is content-based video retrieval, recognition of dynamic textures for compressed video has not been considered. The content of video and dynamic textures in particular, profoundly affect the performance of video compression algorithms. The prominence of compression artifacts can, therefore, be used to recognize dynamic textures in compressed videos. In the paper, we show how features, previously proposed for quality assessment, statistical analysis and a soft computing technique (neural networks) can be used to discern 23 different classes of dynamic textures in a standard video database, with 99.5% accuracy.


Support Vector Machine Video Quality Video Signature Dynamic Texture Spatial Activity 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Babu, V., Andrew, P., Inge, H.O.: Evaluation and monitoring of video quality for UMA enabled video streaming systems. Multimedia Tools Appl. 37(2), 211–231 (2008)CrossRefGoogle Scholar
  2. 2.
    Breiman, L.: Random forests. Machine Learning 45(1), 5–32 (2001)zbMATHCrossRefGoogle Scholar
  3. 3.
    Chan, A., Vasconcelos, N.: Classifying video with kernel dynamic textures. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1–6. IEEE Press, Piscataway (2007)Google Scholar
  4. 4.
    Chetverikov, D., Péteri, R.: A brief survey of dynamic texture description and recognition. Computer Recognition Systems, 17–26 (2005)Google Scholar
  5. 5.
    Culibrk, D., Mirkovic, M., Zlokolica, V., Pokric, M., Crnojevic, V., Kukolj, D.: Salient Motion Features for Video Quality Assessment. IEEE Trans. on Image Processing, 948–958 (2010)Google Scholar
  6. 6.
    Derpanis, K., Wildes, R.: Dynamic texture recognition based on distributions of spacetime oriented structure. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 191–198. IEEE Press, Piscataway (2010)Google Scholar
  7. 7.
    Ferzli, R., Karam, L.: A no-reference objective image sharpness metric based on just-noticeable blur and probability summation. In: Proc. IEEE Conf. on Image Processing (ICIP), pp. III:445–III:448. IEEE Press, Piscataway (2007)Google Scholar
  8. 8.
    Haskell, B., Puri, A., Netravali, A.: Digital video: an introduction to MPEG-2. Kluwer, Amsterdam (1997)Google Scholar
  9. 9.
    Haykin, S.: Neural Networks: A Comprehensive Foundation. Macmillan, New York (1994)zbMATHGoogle Scholar
  10. 10.
    Kim, K., Davis, L.: A fine-structure image/video quality measure using local statistics. In: Proc. IEEE Conf. on Image Processing V, pp. 3535–3538 (2004)Google Scholar
  11. 11.
    Kirenko, I.: Reduction of coding artifacts using chrominance and luminance spatial analysis. In: Proc. Int. Conf. on Consumer Electronics (ICCE), pp. 209–210 (2006)Google Scholar
  12. 12.
    Péteri, R., Fazekas, S., Huiskes, M.: DynTex: A comprehensive database of Dynamic Textures. Pattern Recognition Letters (2010)Google Scholar
  13. 13.
    Ravichandran, A., Chaudhry, R., Vidal, R.: View-invariant dynamic texture recognition using a bag of dynamical systems. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1651–1657. IEEE Press, Piscataway (2009)Google Scholar
  14. 14.
    Richardson, I.: H.264 and MPEG-4 video compression. Wiley Online Library (2003)Google Scholar
  15. 15.
    Saisan, P., Doretto, G., Wu, Y., Soatto, S.: Dynamic texture recognition (2001)Google Scholar
  16. 16.
    Schapire, R.: The boosting approach to machine learning: An overview. In: Nonlinear Estimation and Classification, pp. 149–172. Springer, New York (2003)Google Scholar
  17. 17.
    Schwenk, H., Bengio, Y.: Boosting neural networks. Neural Computation 12(8), 1869–1887 (2000)CrossRefGoogle Scholar
  18. 18.
    Wang, Z., Lu, L., Bovik, A.: Video quality assessment based on structural distortion measurement. Signal Processing: Image Communication 19(2), 121–132 (2004)CrossRefGoogle Scholar
  19. 19.
    Wang, Z., Sheikh, H.R., Bovik, A.C.: No-reference perceptual quality assessment of jpeg compressed images. In: Proc. IEEE Int. Conf. on Image Processing, pp. 477–480 (2002)Google Scholar
  20. 20.
    Warwick, G., Thong, N.: Signal Processing for Telecommunications and Multimedia. In: Classification of Video Sequences in MPEG Domain, ch. 6. Springer, New York (2004)Google Scholar
  21. 21.
    Winkler, S.: Digital video quality: vision models and metrics. J. Wiley & Sons, Chichester (2005)Google Scholar
  22. 22.
    Witten, I.H., Frank, E.: Data Mining: Practical machine learning tools and techniques, 2nd edn. Morgan Kaufmann, San Francisco (2005)zbMATHGoogle Scholar
  23. 23.
    Wolf, S., Pinson, M.: Spatial-temporal distortion metrics for in-service quality monitoring of any digital video system. In: Proc. Int. Symp. on Voice, Video, and Data Communications. SPIE, Boston (1999)Google Scholar
  24. 24.
  25. 25.
    Zechner, M., Granitzer, M.: Accelerating k-means on the graphics processor via CUDA. In: Proc. Int. Conf. on Intensive Applications and Services (INTENSIVE 2009). IEEE Press, Piscataway (2009)Google Scholar
  26. 26.
    Zhao, G., Pietikainen, M.: Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 915–928 (2007)Google Scholar

Copyright information

© Springer-Verlag GmbH Berlin Heidelberg 2013

Authors and Affiliations

  • Dubravko Ćulibrk
    • 1
  • Matei Mancas
    • 2
  • Vladimir Ćrnojevic
    • 1
  1. 1.University of Novi SadNovi SadSerbia
  2. 2.University of MonsMonsBelgium

Personalised recommendations