Supporting visual quality assessment with machine learning

Springer Science and Business Media LLC - Tập 2013 - Trang 1-15 - 2013
Paolo Gastaldo1, Rodolfo Zunino1, Judith Redi2
1Department of Electric, Electronic, Telecommunication Engineering and Naval Architecture (DITEN), University of Genoa, Genova, Italy
2Intelligent Systems Department, Delft University of Technology, Delft, The Netherlands

Tóm tắt

Objective metrics for visual quality assessment often base their reliability on the explicit modeling of the highly non-linear behavior of human perception; as a result, they may be complex and computationally expensive. Conversely, machine learning (ML) paradigms allow to tackle the quality assessment task from a different perspective, as the eventual goal is to mimic quality perception instead of designing an explicit model the human visual system. Several studies already proved the ability of ML-based approaches to address visual quality assessment; nevertheless, these paradigms are highly prone to overfitting, and their overall reliability may be questionable. In fact, a prerequisite for successfully using ML in modeling perceptual mechanisms is a profound understanding of the advantages and limitations that characterize learning machines. This paper illustrates and exemplifies the good practices to be followed.

Tài liệu tham khảo

Hemami SS, Reibman AR: No-reference image and video quality estimation: applications and human-motivated design. Signal Processing: Image Commun 2010, 25(7):469-481. 10.1016/j.image.2010.05.009 Lin W, Jay Kuo C-C: Perceptual visual quality metrics: a survey. J. Visual Commun. Image Representation 2011, 22(4):297-312. 10.1016/j.jvcir.2011.01.005 VQEG, Final report from the video quality experts group on the validation of objective models of video quality assessment. 2003. . Accessed 3 September 2013 http://www.vqeg.org/ Gastaldo P, Redi JA: Machine learning solutions for objective visual quality assessment. Paper presented at the 6th international workshop on video processing and quality metrics for consumer electronics, VPQM-12. Scottsdale; 2012. http://enpub.fulton.asu.edu/resp/vpqm/vpqm12/ Lin F-H, Mersereau RM: Rate–quality tradeoff MPEG video encoder. Signal Processing: Image Commun 1999, 14: 297-309. 10.1016/S0923-5965(98)00014-9 Gastaldo P, Rovetta S, Zunino R: Objective quality assessment of MPEG-2 video streams by using CBP neural networks. IEEE Trans. on Neural Networks 2002, 13(4):939-947. 10.1109/TNN.2002.1021894 Yao S, Lin W, Lu Z, Ong E, Yang X: Video quality assessment using neural network based on multi-feature extraction. Proceedings of the SPIE, Lugano, vol. 5150. In Visual Communications and Image Processing. Edited by: Ebrahimi T, Sikora T. SPIE, Bellingham; 2003:604. Le Callet P, Viard-Gaudin C, Barba D: A convolutional neural network approach for objective video quality assessment. IEEE Trans Neural Networks 2006, 17(5):1316-1327. 10.1109/TNN.2006.879766 Kanumuri S, Cosman P, Reibman A, Vaishampayan V: Modeling packet-loss visibility in MPEG-2 video. IEEE Transactions on Multimedia 2006, 8(2):341-355. El Khattabi H, Tamtaoui A, Aboutajdine D: Video quality assessment measure with a neural network. Int. J. Comput. Inf. Eng 2010, 4(3):167-171. Narwaria M, Lin W, Anmin L: Low-complexity video quality assessment using temporal quality variations. IEEE Trans Multimedia 2012, 14(3):525-535. Staelens N, Deschrijver D, Vladislavleva E, Vermeulen B, Dhaene T, Demeester P: Constructing a no-reference H.264/AVC bitstream-based video quality metric using genetic programming-based symbolic regression. IEEE Trans on Circuits Systems Video Technol 2013, 23(8):1322-1333. Gastaldo P, Zunino R: Neural networks for the no-reference assessment of perceived quality. SPIE J Electron Imaging 2005, 14: 033004. 10.1117/1.1988313 Suresh S, Babu RV, Kim HJ: No-reference image quality assessment using modified extreme learning machine classifier. Applied Soft Computing 2009, 9: 541-552. 10.1016/j.asoc.2008.07.005 Narwaria M, Lin W: Objective image quality assessment based on support vector regression. IEEE Trans. Neural Networks 2010, 21(3):515-519. Redi J, Gastaldo P, Heynderickx I, Zunino R: Color distribution information for the reduced-reference assessment of perceived image quality. IEEE Trans. Circ. Syst. Video Technol 2010, 20(12):1757-1769. Liu H, Redi J, Alers H, Zunino R, Heynderickx I: An efficient neural-network based no-reference approach to an overall quality metric for JPEG and JPEG2000 compressed images. SPIE J. of Elect. Imaging 2011, 20(4):1-15. Li C, Bovik AC, Wu X: Blind image quality assessment using a general regression neural network. IEEE Trans Neural Networks 2011, 22(5):793-799. Moorthy AK, Bovik AC: Blind image quality assessment: from natural scene statistics to perceptual quality. IEEE Trans. Image Proc 2011, 20(12):3350-3364. Tang H, Joshi N, Kapoor A IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs. In Learning a blind measure of perceptual image quality. IEEE, Piscataway; 2011:305. Decherchi S, Gastaldo P, Redi J, Zunino R, Cambria E: Circular-ELM for the reduced-reference assessment of perceived image quality. Neurocomputing 2013, 102: 78-89. Charrier C, Lézoray O, Lebrun G: Machine learning to design full-reference image quality assessment algorithm. Signal Processing: Image Communication 2012, 27: 209-219. 10.1016/j.image.2012.01.002 Narwaria M, Lin W, Enis A: Cetin, Scalable image quality assessment with 2D mel-cepstrum and machine learning approach. Pattern Recognition 2012, 45: 299-313. 10.1016/j.patcog.2011.06.023 Narwaria M, Lin W: SVD-based quality metric for image and video using machine learning. IEEE Trans. on Systems, Man and Cybernetics, Part B. Cybernetics 2012, 42(2):347-364. Thiede T, Treurniet W, Bitto R, Schmidmer C, Sporer T, Beerends J, Colomes C, Keyhl M, Stoll G, Brandenburg K, Feiten B: PEAQ—the ITU standard for objective measurement of perceived audio quality. J. Audio Eng. Soc 2000, 48(1/2):3-29. Sebe N, Cohen I, Garg A, Huang TS: Machine Learning in Computer Vision. Springer, Dordrecht; 2005. Da San Martino G, Sperduti A: Mining structured data. IEEE Comput. Intell. Mag 2010, 5: 42-49. Rajapakse JC, Zhang Y-Q, Fogel GB IEEE/ACM Transactions on Computational Biology and Bionformatics. Computational intelligence approaches in computational biology and bioinformatics, vol 4 2007. Bishop CM: Pattern Recognition and Machine Learning. Springer, Dordrecht; 2006. Guyon I, Elisseeff A: An introduction to variable and feature selection. J. Mach. Learn. Res 2003, 3: 1157-1182. van der Maaten L, Postma E, van den Herik J: Dimensionality reduction: a comparative review. J Mach. Learn. Res 2009, 10: 1-41. Vapnik V: Statistical Learning Theory. Wiley, New York; 1998. Misra J, Saha I: Artificial neural networks in hardware: a survey of two decades of progress. Neurocomputing 2010, 74: 239-255. 10.1016/j.neucom.2010.03.021 Rumelhart DE, McClelland JL: Parallel Distributed Processing. MIT Press, Cambridge; 1986. Hornik K, Stinchcombe M, White H: Multilayer feedforward networks are universal approximators. Neural Networks 1989, 2(5):359-356. 10.1016/0893-6080(89)90020-8 Baum EB, David H: What size net gives valid generalization? Neural Comput 1989, 1(1):151-160. 10.1162/neco.1989.1.1.151 Widrow B, Lehr MA: 30 years of adaptive neural networks: perceptron Madaline and back propagation. Proc. IEEE 1990, 78(9):1415-1442. 10.1109/5.58323 Koza JR: Genetic programming as a means for programming computers by natural selection. Stat Comput 1994, 4(2):87-112. Filho JLR, Treleaven PC, Alippi C: Genetic-algorithm programming environments. IEEE Computer 1994, 27(6):28-43. Espejo PG, Ventura S, Herrera FG: A survey on the application of genetic programming to classification. IEEE Trans. Systems, Man, and Cybernetics, Part C: Applications and Reviews 2010, 40(2):121-144. Moody JE: The effective number of parameters: an analysis of generalization and regularization in nonlinear learning systems. In Advances in Neural Information Processing Systems 4. Edited by: Moody JE, Hanson SJ, Lippmann RP. Morgan Kaufmann, San Mateo; 1992:847. Fliegel K, Timmerer C: WG4 Databases Whitepaper v1.5: QUALINET multimedia database enabling QoE evaluations and benchmarking (QUALINET, COST Action IC1003, 2013). . Accessed 3 September 2013 http://dbq-wiki.multimediatech.cz/_media/qi0306.pdf Seshadrinathan K, Soundararajan R, Bovik A, Cormack L: Study of subjective and objective quality assessment of video. IEEE Trans. Image Process 2010, 19(6):1427-1441. Simone F, Naccari M, Tagliasacchi M, Dufaux F, Tubaro S, Ebrahimi T Proceedings of the 1st International Workshop on Quality of Multimedia Experience, QoMEX 2009, San Diego. In Subjective assessment of H.264/AVC video sequences transmitted over a noisy channel. IEEE, Piscataway; 2009:204. LIVE Image Quality Assessment Database (Laboratory for Image & Video Engineering, The University of Texas at Austin). . Accessed 3 September 2013 http://live.ece.utexas.edu/research/quality/ Ponomarenko N, Carli M, Lukin V, Egiazarian K, Astola J, Battisti F Proceedings of IEEE 10th Workshop on Multimedia Signal Processing, Cairns. In Color image database for evaluation of image quality metrics. IEEE, Piscataway; 2008:403. Larson E, Chandler D: Most apparent distortion: full-reference image quality assessment and the role of strategy. SPIE J. on Electron. Imag 2010, 19(1):011006. 10.1117/1.3267105 Subjective Quality Assessment IRCCyN/IVC Database (IVC, Institut de Recherche en Communications et Cybernétique de Nantes). . Accessed 3 September 2013 http://www2.irccyn.ec-nantes.fr/ivcdb/ Image Quality Evaluation Database (MICT, University of Toyama). . Accessed 3 September 2013 http://160.26.142.130/toyama_database.zip Pinson MH, Wolf S: Comparing subjective video quality testing methodologies. Proceedings of the SPIE, Lugano. In Visual Communications and Image Processing, vol. 5150. Edited by: Ebrahimi T, Sikora T. SPIE, Bellingham; 2003:573. Specht DF: A general regression neural network. IEEE Trans. Neural Networks 1991, 2(6):568-576. 10.1109/72.97934 Huang G-B, Wang D, Lan Y: Extreme learning machines: a survey. Int. J. Mach. Learn. Cybern 2011, 2(2):107-122. 10.1007/s13042-011-0019-y Argyropoulos S, Raake A, Garcia M-N, List P: No-reference video quality assessment of SD and HD H.264/AVC sequences based on continuous estimates of packet loss visibility. In Proceedings of the 3rd International Workshop Quality of Multimedia Experience, QoMEX 2011, Mechelen. IEEE, Piscataway; 2011:31. Ridella S, Rovetta S, Zunino R: Circular back-propagation networks for classification. IEEE Trans. Neural Networks 1997, 8(1):84-97. 10.1109/72.554194 Strohmeier D, Kunzem K, Göbel K, Liebetrau J: Evaluation of differences in quality of experience features for test stimuli of good-only and bad-only overall audio visual quality. Proceedings of the SPIE, Burlingame, 3. In Image Quality and System Performance X, vol. 8653. Edited by: Burns PD, Triantaphillidou S. SPIE, Bellingham; 2013. doi:10.1117/12.2001363 Chetouani A, Beghdadi A: Image quality assessment based on distortion identification. Proceedings of the SPIE, San Francisco. In Image Quality and System Performance VIII, vol. 7867. Edited by: Farnand SP, Gaykema F. SPIE, Bellingham; 2011. doi:10.1117/12.876308 Simoncelli EP, Freeman WT, Adelson EH, Heeger DJ: Shiftable multiscale transforms. IEEE Trans. Inf. Theory 1992, 38(2):587-607. 10.1109/18.119725 Wang Z, Bovik AC: A universal quality index. IEEE Transactions on Image Processing 2002, 9(3):81-84. Dempster A: Upper and lower probabilities induced by multi-valued mapping. Annals of Math. Stat 1967, 38: 325-339. 10.1214/aoms/1177698950 Wang Z, Bovik A, Sheikh H, Simoncelli E: Image quality assessment: from error measurement to structural similarity. IEEE Trans. Image Process 2004, 13(1):1-14. Moorthy AK, Bovik AC: A two-step framework for constructing blind image quality indices. IEEE Signal Processing Letters 2010, 17(5):513-516. Saad MA, Bovik AC: Blind image quality assessment: a natural scene statistics approach in the DCT domain. IEEE Transactions on Image Processing 2012, 21(8):3339-3352. International Telecommunication Union (ITU): Objective perceptual video quality measurement techniques for digital cable television in the presence of a full reference. Rec J 2004., 144: Chang C-C, Lin C-J: LIBSVM: a library for support vector machines. ACM Trans. on Intelligent Systems and Technology 2011, 2(3):1-39. doi:10.1145/1961189.1961199 International Telecommunication Union (ITU): BT.500–11: Methodology for the Subjective Assessment of the Quality of Television Pictures. ITU, Geneva; 2002. Redi J, Liu H, Zunino R, Heynderickx I: Comparing subjective image quality measurement methods for the creation of public databases. Proceedings of the SPIE, San Jose. In Image Quality and System Performance VII, vol. 7529. Edited by: Farnand SP, Gaykema F. SPIE, Bellingham; 2010. doi:10.1117/12.839195 Chapelle O, Schòlkopf B, Zien A: Semi-Supervised Learning. MIT Press, Cambridge; 2006.