Advertisement

Measure a Subjective Video Quality Via a Neural Network

  • Hasnaa El Khattabi
  • Ahmed Tamtaoui
  • Driss Aboutajdine
Part of the Communications in Computer and Information Science book series (CCIS, volume 166)

Abstract

We present in this paper a new method to measure the quality of the video in order to change the judgment of the human eye by an objective measure. This latter predicts the mean opinion score (MOS) and the peak signal to noise ratio (PSNR) by providing eight parameters extracted from original and coded videos. These parameters that are used are: the average of DFT differences, the standard deviation of DFT differences, the average of DCT differences, the standard deviation of DCT differences, the variance of energy of color, the luminance Y, the chrominance U and the chrominance V. The results we obtained for the correlation show a percentage of 99.58% on training sets and 96.4% on the testing sets. These results compare very favorably with the results obtained with other methods [1].

Keywords

video neural network MLP subjective quality objective quality luminance chrominance 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Lin, F.H., Mersereau, R.M.: Rate-quality tradeoff MPEG video encoder. Signal Processing : Image Communication 14, 297–300 (1999)Google Scholar
  2. 2.
    Wang, Z., Bovik, A.C.: Modern Image Quality Assessment. Morgan & Claypool Publishers, USA (2006)Google Scholar
  3. 3.
    Pinson, M., Wolf, S.: Comparing subjective video quality testing methodologies. In: SPIE Video Communications and Image Processing Conference, Lugano, Switzerland (July 2003) Google Scholar
  4. 4.
    Zurada, J.M.: Introduction to artificial neural system. PWS Publishiner Company (1992)Google Scholar
  5. 5.
    Malo, J., Pons, A.M., Artigas, J.M.: Subjective image fidelity metric based on bit allocation of the human visual system in the DCT domain. Image and Vision Computing 15, 535–548 (1997)CrossRefGoogle Scholar
  6. 6.
    Watson, A.B., Hu, J., McGowan, J.F.: Digital video quality metric based on human vision. Journal of Electronic Imaging 10(I), 20–29 (2001)CrossRefGoogle Scholar
  7. 7.
    Sun, H.M., Huang, Y.K.: Comparing Subjective Perceived Quality with Objective Video Quality by Content Characteristics and Bit Rates. In: International Conference on New Trends in Information and Service Science, niss, pp. 624–629 (2009)Google Scholar
  8. 8.
    Huynh-Thu, Q., Ghanbari, M.: Scope of validity of PSNR in image/video quality assessment. Electronics Letters 44(13), 800–801 (2008)CrossRefGoogle Scholar
  9. 9.
    Wang, Z., Bovik, A.C.: Mean squared error: love it or leave it. IEEE Signal Process Mag. 26(1), 98–117 (2009)CrossRefGoogle Scholar
  10. 10.
    Sheikh, H.R., Bovik, A.C., Veciana, G.d.: An Information Fidelity Criterion for Image Quality Assessment Using Natural Scene Statistics. IEEE Transactions on Image Processing 14(12), 2117–2128 (2005)CrossRefGoogle Scholar
  11. 11.
    Juan, D., Yinglin, Y., Shengli, X.: A New Image Quality Assessment Based On HVS. Journal Of Electronics 22(3), 315–320 (2005)Google Scholar
  12. 12.
    Bouzerdoum, A., Havstad, A., Beghdadi, A.: Image quality assessment using a neural network approach. In: The Fourth IEEE International Symposium on Signal Processing and Information Technology, pp. 330–333 (2004)Google Scholar
  13. 13.
    Beghdadi, A., Pesquet-Popescu, B.: A new image distortion measure based on wavelet decomposition. In: Proc.Seventh Inter. Symp. Signal. Proces. Its Application, vol. 1, pp. 485–488 (2003)Google Scholar
  14. 14.
    Slanina, M., Ricny, V.: Estimating PSNR without reference for real H.264/AVC sequence intra frames. In: 18th International Conference on Radioelektronika, pp. 1–4 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Hasnaa El Khattabi
    • 1
  • Ahmed Tamtaoui
    • 2
  • Driss Aboutajdine
    • 1
  1. 1.LRITUnité associée au CNRST, URAC 29, Faculté des SciencesRabatMorocco
  2. 2.Institut National Des Postes et Télécommunications (INPT)RabatMorocco

Personalised recommendations