Е.А. Pavlov - Post-graduate, Demidov Yaroslavl State University. E-mail: evgeny@pavlov.name
О.N. Gushchina - Post-graduate, Demidov Yaroslavl State University. E-mail: olyagushchina@gmail.com
А.L. Priorov - Dr.Sci. (Eng.), Demidov Yaroslavl State University. E-mail: andcat@yandex.ru
V.V. Khryashchev - Ph.D. (Eng.), Demidov Yaroslavl State University. E-mail: vhr@yandex.ru

The task of objective image quality assessment is inextricably linked with the development of algorithms that could automatically determine the quality of the image. Human is an end user of visual information, thus development of such criteria, which allowed us to estimate the image quality as people would rate is important. Adequacy of objective quality assessment algorithms and their comparison are performed by measuring the degree of correlation of these algorithms with mean option score. Various statistical factors, such as the Spearman-s rank correlation coefficient, Pearson-s linear correlation, the value of the mean square error are used in practice. High value of the coefficients of linear correlation and Spearman correlation indicates the adequacy of the algorithm. Currently, the most urgent problem is the development of non-reference algorithms whose work is possible without using the original undistorted (reference) image, which in practice is usually not available. At the same time non-reference quality assessment algorithms is limited only to certain kinds of distortions: for example, blurring artifacts in compression JPEG and JPEG2000 and others. In this paper a new universal algorithm for non-reference image quality evaluation based on statistics of discrete cosine transform (DCT) coefficients and the training procedure based on image LIVE are proposed. Experimental results demonstrate that proposed algorithm can be effectively used for quality assessment of noised and compressed images as wells as for denoising and deblocking algorithms comparison.

 

1. Gonsales R., Vuds R. Cifrovaya obrabotka izobrazhenij. M.: Texnosfera. 2005.
2. Kravchenko V.F. Cifrovaya obrabotka signalov i izobrazhenij v radiofizicheskix prilozheniyax. M.: Fizmatlit. 2007.
3. Priorov A.L., Apal'kov A.V., Xryashhev V.V. Cifrovaya obrabotka izobrazhenij. Jaroslavl': Jarosl. gos. universitet. 2007.
4. Chen M.J., Bovik A.C. No reference image blur assessment using multiscale gradient // 1st International Workshop on Quality of Multimedia Experience (QoMEX). 2009.
5. Marziliano P., Dufaux F., Winkler S., Ebrahimi T. Perceptual blur and ringing metrics: application to JPEG2000 // Sig. Proc.: Image Comm. 2004. V. 19. № 2. P. 163-172.
6. Wang Z., Sheikh H.R., Bovik A.C. No-reference perceptual quality assessment of JPEG compressed images // IEEE Int'l Conf. Image Proc. 2002. P. 477-480.
7. Gerasimov N.B., Gushhina O.N., Pavlov E.A. Metod nee'talonnoj oczenki kachestva izobrazhenij na osnove statisticheskoj modeli iskazhenij // Trudy' LXVI Nauch. sessii, posvyashhennoj Dnyu Radio. Moskva. 2011. S. 347-350.
8. Priorov A.L., Apal'kov I.V., Gerasimov N.B., Pavlov E.A. Algoritmy' oczenki kachestva videoposledovatel'nostej, szhaty'x po standartu Motion JPEG2000 // Uspexi sovremennoj radioe'lektroniki. 2012. № 10. S. 59-65.
9. Ong E.P., Lin W., Lu Z., Yao S., Yang X., Jiang L. No-refer­ence JPEG-2000 image quality metric // International Conference on Multimedia and Expo. 2003. V. 1. P. 6-9.
10. Moorthy A.K., Bovik A.C. A two-step framework for constructing blind image quality indices // IEEE Signal Proces­sing Letters. 2010. V. 17. № 2. P. 587-599.
11. Saad M.A., Bovik A.C., Charrier C. A DCT Statistics-based blind image quality index // IEEE Signal Processing Letters. 2010. V. 17. № 6. P. 583-586.
12. Wang Z., Wu G., Sheikh H.R., Simoncelli E.P., Yang E.H., Bovik A.C. Quality aware images // IEEE Transactions on Image Processing. 2006. V. 15. № 6. P. 1680-1689.
13. Mittal A., Moorthy A.K., Bovik A.C. No-reference image quality assessment in the spatial domain // IEEE Transactions on Image Processing. 2012.
14. Mittal A., Soundararajan R., Bovik A.C. Making a completely blind image quality analyzer // IEEE Signal processing Letters. 2013. V. 22. № 3. P. 209-212.
15. Sheikh H.R., Wang Z., Cormack L., Bovik A.C. LIVE image quality assessment database release 2, 2006. http://live.ece.ute­xas.edu/research/ quality/subjective.htm
16. Datta R., Joshi D., Li J., Wang J.Z. Studying aesthetics in photographic images using a computational approach // Lec. Notes. in Comp. Sci. 2006. P. 288.
17. Bovik A. The handbook of image and video processing (com­munication, networking and multimedia). Academic Press, 2005.
18. Li C., Chen T. Aesthetic visual quality assessment of paintings // IEEE Jnl. Sel. Top. Sig. Proc. 2009. V. 3. № 2. P. 236-252.
19. Sharifi K., Leon-Garcia A. Estimation of shape parameter for generalized Gaussian distributions in sub-band decompositions of video // IEEE Trans. Circuits Syst. Video Technol. 2005. V. 5. № 1. P. 52-56.
20. Sheikh H.R., Bovik A.C. Image information and visual quality // IEEE Transactions on Image Proc. 2006. V. 15. № 2. P. 430-444.
21. Tomasi C., Manduchi R. Bilateral filtering for gray and color images // Sixth Int. Conf. on Comp. Vis. 1998. P. 839-846.
22. Elad M. On the origin of the bilateral filter and ways to improve it // IEEE Trans. on Image Proc. 2002. V. 11. № 10. P. 1141-1151.
23. Priorov A.L., Xryashhev V.V., Pavlov E.A., Gerasimov N.B., Shemyakov A.M. Oczenka kachestva czvetny'x izobrazhenij pri podavlenii impul'snogo shuma // Radiotexnika. 2013. S. 41-49.
24. Ganin A.N., Gushhina O.N., Xryashhev V.V. Analiz primeneniya adaptivnogo diskretnogo kosinusnogo preobrazovaniya v nekotory'x zadachax czifrovoj obrabotki izobrazhenij // Uspexi sovremennoj radioe'lektroniki. 2011. № 2. S. 72-80.
25. Gushhina O.N., Solov'ev E.V., Ganin A.N. Udalenie arte­faktov blochnosti iz szhaty'x izobrazhenij s ispol'zova­niem adaptivnogo diskretnogo kosinusnogo preobrazova­niya // Dokl. 13-j Mezhdunar. konf. «Cifrovaya obrabotka signalov i ee primenenie», M. 2011. T. 2. S. 119-122.