GPGPU Based Estimation of the Combined Video Quality Metric

  • Krzysztof Okarma
  • Przemysław Mazurek
Conference paper
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 102)

Summary

In this paper some possibilities of using the GPGPU programming techniques for a fast estimation of the recently proposed combined video quality metric are discussed. Such metric consists of three state-of-the-art image quality assessment metrics applied using frame-by-frame analysis with appropriate weighting coefficients. Since this combined metric is better correlated with subjective quality scores than each of its components, especially for the contaminations typical for the wireless transmission of compressed video data, the next step is related to its efficient implementation useful for real-time applications. In the paper an efficient implementation of the estimated combined metric is presented together with the verification of its linear correlation with subjective video quality evaluations performed using the LIVE Wireless Video Quality Assessment Database containing 160 video files with four types of distortions and their Differential Mean Opinion Score (DMOS) values.

Keywords

Video Quality Image Quality Assessment Structural Similarity Index SSIM Index Video Quality Assessment 
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.
    Wang, Z., Bovik, A.: A universal image quality index. IEEE Signal Proc. Letters 9(3), 81–84 (2002)CrossRefGoogle Scholar
  2. 2.
    Eskicioglu, A.: Quality measurement for monochrome compressed images in the past 25 years. In: Proc. Int. Conf. Acoust. Speech Signal Proc., pp. 1907–1910 (2000)Google Scholar
  3. 3.
    Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: From error measurement to Structural Similarity. IEEE Trans. Image Proc. 13(4), 600–612 (2004)CrossRefGoogle Scholar
  4. 4.
    Wang, Z., Simoncelli, E., Bovik, A.: Multi-Scale Structural Similarity for image quality assessment. In: Proc. 37th IEEE Asilomar Conf. on Signals, Systems and Computers (2003)Google Scholar
  5. 5.
    Okarma, K.: Two-dimensional windowing in the Structural Similarity index for the colour image quality assessment. In: Jiang, X., Petkov, N. (eds.) CAIP 2009. LNCS, vol. 5702, pp. 501–508. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  6. 6.
    Sheikh, H.R., Bovik, A., de Veciana, G.: An information fidelity criterion for image quality assessment using natural scene statistics. IEEE Trans. Image Proc. 14(12), 2117–2128 (2005)CrossRefGoogle Scholar
  7. 7.
    Sheikh, H.R., Bovik, A.: Image information and visual quality. IEEE Trans. Image Proc. 15(2), 430–444 (2006)CrossRefGoogle Scholar
  8. 8.
    Okarma, K.: Video quality assessment using the combined full-reference approach. In: Choras, R. (ed.) Image Processing and Communications Challenges 2. AISC, vol. 84, pp. 51–58. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  9. 9.
    Moorthy, A.K., Seshadrinathan, K., Soundararajan, R., Bovik, A.: Wireless video quality assessment: A study of subjective scores and objective algorithms. IEEE Trans. Circuits and Systems for Video Technology 20(4), 513–516 (2010)CrossRefGoogle Scholar
  10. 10.
    Moorthy, A.K., Seshadrinathan, K., Soundararajan, R., Bovik, A.: LIVE Wireless Video Quality Assessment Database (2009), http://live.ece.utexas.edu/research/quality/live_wireless_video.html
  11. 11.
    Okarma, K.: Combined full-reference image quality metric linearly correlated with subjective assessment. In: Rutkowski, L., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M., et al. (eds.) ICAISC 2010. LNCS(LNAI), vol. 6113, pp. 539–546. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  12. 12.
    Mansouri, A., Mahmoudi-Aznaveh, A., Torkamani-Azar, F., Jahanshahi, J.A.: Image quality assessment using the Singular Value Decomposition theorem. Optical Review 16(2), 49–53 (2009)CrossRefGoogle Scholar
  13. 13.
    Shnayderman, A., Gusev, A., Eskicioglu, A.: A multidimensional image quality measure using Singular Value Decomposition. In: Proc. SPIE Image Quality and Syst. Perf., vol. 5294(1), pp. 82–92 (2003)Google Scholar
  14. 14.
    Shnayderman, A., Gusev, A., Eskicioglu, A.: An SVD-based gray-scale image quality measure for local and global assessment. IEEE Trans. Image Proc. 15(2), 422–429 (2006)CrossRefGoogle Scholar
  15. 15.
    Mahmoudi-Aznaveh, A., Mansouri, A., Torkamani-Azar, F., Eslami, M.: Image quality measurement besides distortion type classifying. Optical Review 16(1), 30–34 (2009)CrossRefGoogle Scholar
  16. 16.
    Okarma, K.: Colour image quality assessment using Structural Similarity index and Singular Value Decomposition. In: Bolc, L., Kulikowski, J.L., Wojciechowski, K. (eds.) ICCVG 2008. LNCS, vol. 5337, pp. 55–65. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  17. 17.
    Okarma, K.: Colour image quality assessment using the combined full-reference metric. In: Burduk, R., Kurzyński, M., Woźniak, M., Żołnierek, A., et al. (eds.) Computer Recognition Systems 4. Advances in Intelligent and Soft Computing, vol. 95, pp. 287–296. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  18. 18.
    Mazurek, P., Okarma, K.: An efficient estimation of the Structural Similarity index using the GPGPU programming techniques. Measurement Automation and Monitoring (PAK) 56(7), 668–670 (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Krzysztof Okarma
    • 1
  • Przemysław Mazurek
    • 1
  1. 1.Faculty of Electrical Engineering, Department of Signal Processing and Multimedia EngineeringWest Pomeranian University of TechnologySzczecinPoland

Personalised recommendations