A two-layer neural system for reduced-reference visual quality assessment

• Autorzy: Redi J. , Gastaldo P. , Zunino R.
• Języki publikacji: EN

Abstrakty

EN

Real-time assessment of visual quality can be efficiently supported by reduced-refe-rence paradigms, which require a very limited amount of information on the original signal, easily embeddable in the signal itself. In this paper, a reduced-reference system for image quality assessment is proposed, based on a small sized numerical description of images encoding the luminance distribution and its variations due to visual distortions. The assessment paradigm is implemented exploiting machine learning tools and articulates in two phases: first, a Support Vector Machines-based classifier identifies the kind of distortion affecting the image; then, the actual quality level of the distorted image is computed by a specifically trained SVM regressor. The general validity of the approach is supported by experimental validations based on subjective quality data.

Słowa kluczowe

EN

reduced-reference system; image; visual quality assessmen; luminance distribution; visual distortions; support vector machine; SVM

• Wydawca: University of Social Sciences
• Czasopismo: Journal of Artificial Intelligence and Soft Computing Research
• Rocznik: 2011
• Tom: Vol. 1, No. 1
• Strony: 27--41
• Opis fizyczny: Bibliogr. 40 poz., rys.

Twórcy

autor

Redi J.

• Department Biophysical and Electronic Engineering University of Genoa Via Opera Pia 11/, 16145 Genoa, Italy

autor

Gastaldo P.

• Department Biophysical and Electronic Engineering University of Genoa Via Opera Pia 11/, 16145 Genoa, Italy

autor

Zunino R.

• Department Biophysical and Electronic Engineering University of Genoa Via Opera Pia 11/, 16145 Genoa, Italy

Bibliografia

• [1] V. Baroncini. New tendencies in subjective video quality evaluation. IECIE Transactions on Fundamentals, 11(89):2933–2937, 2006.
• [2] Lugosi G. Bartlett P., Boucheron S. Model selection and error estimation. Machine Learning, 48(1–3):85–113, 2002.
• [3] H.R. Sheikh.and A.C. Bovik. Image information and visual quality. IEEE Transactions on Image Processing, 15(2):430–444, 2006.
• [4] A. Boni D. Anguita, S. Ridella, F. Rivieccio, and D. Sterpi. Theoretical and Practical Model Selection Methods for Support Vector Classifiers, pages 159–179. Springer, 2005.
• [5] P. Engeldrum. Psychometric scaling: a toolkit for imaging systems development. Imcotek Press, Winchester, 2000.
• [6] A.M. Eskicioglu and P.S. Fisher. Image quality measures and their performance. IEEE Trans. on Communications, 43(12):2959–2965, 1995.
• [7] D.D. Giusto G. Ginesu, F. Massidda. A multifactors approach for image quality assessment based on a human visual system model. Signal Processing: Image Communication, 21:316–333, 2006.
• [8] Z. Gao and Y.F. Zheng. Quality constrained compression using dwt-based image quality metric. IEEE Transactions on Circuits and Systems for Video Technology, 18(7):910–922, 2008.
• [9] A.C. Bovik H.R. Sheikh and L. Cormack. Noreference quality assessment using natural scene statistics: Jpeg2000. IEEE Trans. Image Process, 14(11):1918–1927, 2005.
• [10] L. Cormack H.R Sheikh, Z. Wang and A.C. Bovik. Live image quality assessment database at http://live.ece.utexas.edu/research/quality. Technical report.
• [11] M.F. Sabir H.R. Sheikh and A.C. Bovik. A statistical evaluation of recent full reference image quality assessment algorithm. IEEE Trans. Image Processing, 15(11):3441–3452, 2006.
• [12] R.G. Laha I.M. Chakravarti and J. Roy. Handbook of Methods of Applied Statistics, volume I. John Wiley, 1967.
• [13] S. Ravi Kumar J. Huang, M. Mitra, W.J. Zhu, and R. Zabih. Image indexing using color correlograms. In Proc. IEEE CVPR ’97, pages 762–768,1997.
• [14] R.P.W. Duin J. Kittler, M. Hatef and J. Matas. On combining classifiers. IEEE Trans. Pattern Analysis and Machine Intelligence, 20:226–239, 1998.
• [15] Q. Li and Z. Wang. General-purpose reducedreference image quality assessment based on perceptually and statistically motivated image representation. In IEEE International Conference on Image Processing, San Diego, CA, 2008.
• [16] H. Liu and I. Heynderickx. A perceptually relevant no-reference blockiness metric based on local image characteristics. EURASIP Journal on Advances in Signal Processing, 2009.
• [17] D. Barba M. Carnec, P. Le Callet. Objective quality assessment of color images based on a generic perceptual reduced reference. Signal Processing: Image Communication, 23:239–256, 2008.
• [18] I. Van Zyl Marais and W.H. Steyn. Robust defocus blur identification in the context of blind image quality assessment. Signal Processing: Image Communication, 22:833–844, 2007.
• [19] S. Winkler P. Marziliano, F. Dufaux and T. Ebrahimi. Perceptual blur and ringing metrics: application to jpeg2000. Signal Processing: Image Communication, 19:163–172, 2004.
• [20] ITU-T Recommendation P.911. Subjective audiovisual quality assessment methods for multimedia applications. Geneva, 1998.
• [21] T.N. Pappas and R.J. Safranek. Perceptual criteria for image quality evaluation. Stateplace New York: Academic, 2000.
• [22] R.Muijs P.Gastaldo, R. Zunino and I. Heynderickx. Building neural systems for no-reference quality assessment. In Proc. of the First International Workshop on Video Processing and Quality Metrics( VPQM’05), 2005.
• [23] Zunino R. Redi J., Gastaldo P. and Heynderickx I.Co-occurrence matrixes for the quality assessment of coded images. In International Conference on Artificial Neural Networks (ICANN’08), 2008.
• [24] Zunino R. Redi J., Gastaldo P. and SnplaceHeynderickx SnI. Reduced reference assessment of perceived quality by exploiting color information. In Proc. International Conference on Artificial Neural Networks (ICANN’09), 2009.
• [25] K. Shanmugam R.M. Haralick and I. Dinstein. Textural features for image classification. IEEE Trans. On Systems, Man and Cybernetics SMC-3, pages 610–621, 1973.
• [26] D.E. Rumelhart and J.L. McClelland. Parallel distributed processing. MIT Press, Cambridge, MA, 1986.
• [27] E. Bienenstock S. Geman and R. Doursat. Neural networks and the bias/variance dilemma. Neural Computation, 4(1):1–48, 1992.
• [28] S. Rovetta S. Ridella and R. Zunino. Circular back-propagation networks for classification. IEEE Trans. on Neural Networks, 8(1):84–97, 1997.
• [29] B. Schlkopf and A. Smola. Learning with Kernels. MIT Press, Cambridge, MA, 2002.
• [30] H.-J. Zepernick T.M. Kusuma. On perceptual objective quality metrics for in-service picture quality monitoring. In Third ATcrc Telecommunications and Networking Conference and Workshop, Melbourne, Australia, 2003.
• [31] International Telecommunication Union. Methodology for the subjective assessment of the quality of television pictures ITU-R BT.500. 1995.
• [32] V. Vapnik. Statistical Learning Theory. Wiley, New York, 1998.
• [33] S. Winkler. Issues in vision modeling for perceptual video quality assessment. Signal Processing, 78:231–252, 1999.
• [34] E.P. Simoncelli Z. Wang. Reduced-reference image quality assessment using a wavelet-domain natural image statistic model. In Proceedings of SPIE Human Vision and Electronic Imaging X, volume 5666, pages 149–159, San Jose, CA, 2005.
• [35] H.R. Sheikh Z. Wang and A.C. Bovik. Noreference perceptual quality assessment of jpeg compressed images. In IEEE Int. Conf. Image Processing, pages 477–480, Rochester, NY, 2002.
• [36] H.R. Sheikh Z. Wang. and A.C. Bovik. Objective video quality assessment. CRC Press, Boca Raton, FL, 2003.
• [37] H.R. Sheikh Z. Wang, A.C. Bovik and E.P. Simoncelli. Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4), 2004.
• [38] H.R. Sheikh Z. Wang, G. Wu, E.P. Simoncelli, E.H. Yang, and A.C. Bovik. Quality-aware images. IEEE Transactions on Image Processing, 15(6):1680–1689, 2006.
• [39] S.Winkler Z. Yu, H.R. Wu and T. Chen. Visionmodel-based impairment metric to evaluate blocking artifact in digital video. In Proc. IEEE, volume 90, pages 154–169, 2002.
• [40] Y. Horita Z.M. Parvez Sazzad, Y. Kawayoke. No reference image quality assessment for jpeg2000 based on spatial features. Signal Processing: Image Communication, 23:257–268, 2008.