Video Quality assessment Measure with a Neural Network

Authors: H. El Khattabi, A. Tamtaoui, D. Aboutajdine

Abstract:

In this paper, we present the video quality measure estimation via a neural network. This latter predicts MOS (mean opinion score) by providing height parameters extracted from original and coded videos. The eight 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. We chose Euclidean Distance to make comparison between the calculated and estimated output.

Keywords: video, neural network MLP, subjective quality, DCT, DFT, Retropropagation

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1330215

References:

[1] F-H Lin, R. M. Mersereau: Rate-quality tradeoff MPEG video encoder. Signal Processing Image Communication 14 1999 297-309.
[2] Z. Wang, A. C. Bovik, (2006), Modern Image Quality Assessment, Morgan & Claypool Publishers, USA.
[3] M. Pinson, S. Wolf, (July 2003), Comparing subjective video quality testing methodologies. SPIE Video Communications and Image Processing Conference, Lugano, Switzerland.
[4] J. M. Zurada, (1992), Introduction to artificial neural system, PWS Publishiner Company.
[5] J. Malo, A. M. Pons, and J. M. Artigas,( 1997), Subjective image fidelity metric based on bit allocation of the human visual system in the DCT domain, Image and Vision Computing, Vol. 15, pp. 535-548.
[6] A. B. Watson, J. Hu, and J. F. McGowan, (2001), Digital video quality metric based on human vision, Journal of Electronic Imaging, Vol. 10, No. I, pp. 20-29.
[7] H.M. Sun, Y.K. Huang, (2009), Comparing Subjective Perceived Quality with Objective Video Quality by Content Characteristics and Bit Rates, 2009 International Conference on New Trends in Information and Service Science, niss, pp.624-629.
[8] Q .Huynh-Thu,M. Ghanbari (2008) ,Scope of validity of PSNR in image/video quality assessment, Electronics Letters, vol. 44,No.13,pp.800-801.
[9] Z .Wang, A.C.Bovik (2009), Mean squared error: love it or leave it?, IEEE Signal Process Mag, vol.26, No.1,pp.98-117.
[10] H. R.Sheikh, A.C.Bovik, G.d. Veciana,(2005), An Information Fidelity Criterion for Image Quality Assessment Using Natural Scene Statistics, IEEE TRANSACTIONS ON IMAGE PROCESSING,vol. 14, NO. 12,pp. 2117- 2128.
[11] D.Juan,Y.Yinglin,X.Shengli,(2005),A New Image Quality Assessment Based On HVS,Journal Of Electronics ,vol.22,No.3,pp.315-320.
[12] A.Bouzerdoum,A.Havstad,A.Beghdadi,(2004),Image quality assessment using a neural network approach,the Fourth IEEE International Symposium on Signal Processing and Information Technology,pp. 330- 333.
[13] A.Beghdadi,B.Pesquet-Popescu,(2003),A new image distortion measure based on wavelet decomposition,Proc.Seventh Inter.symp.Signal. Proces. its Appricatiom , Vol. 1, pp. 485- 488.
[14] Slanina, M. Ricny, V.,(2008), Estimating PSNR without reference for real H.264/AVC sequence intra frames , Radioelektronika, 2008 18th International Conference,pp.1-4.
[15] ITU-R BT.500-1, (2002), Methodology for the subjective assessment of the quality of television pictures