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

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.

[1]  Stefan Winkler,et al.  Perceptual blur and ringing metrics: application to JPEG2000 , 2004, Signal Process. Image Commun..

[2]  Zhou Wang,et al.  No-reference perceptual quality assessment of JPEG compressed images , 2002, Proceedings. International Conference on Image Processing.

[3]  Thrasyvoulos N. Pappas,et al.  Perceptual criteria for image quality evaluation , 2005 .

[4]  Alan C. Bovik,et al.  No-reference quality assessment using natural scene statistics: JPEG2000 , 2005, IEEE Transactions on Image Processing.

[5]  Davide Anguita,et al.  Theoretical and Practical Model Selection Methods for Support Vector Classifiers , 2004 .

[6]  Sandro Ridella,et al.  Circular backpropagation networks for classification , 1997, IEEE Trans. Neural Networks.

[7]  Peter L. Bartlett,et al.  Model Selection and Error Estimation , 2000, Machine Learning.

[8]  Patrick Le Callet,et al.  Objective quality assessment of color images based on a generic perceptual reduced reference , 2008, Signal Process. Image Commun..

[9]  Judith Redi,et al.  Hybrid Neural Systems for Reduced-Reference Image Quality Assessment , 2009, ICANN.

[10]  Zhou Wang,et al.  General-purpose reduced-reference image quality assessment based on perceptually and statistically motivated image representation , 2008, 2008 15th IEEE International Conference on Image Processing.

[11]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .

[12]  D. Brillinger,et al.  Handbook of methods of applied statistics , 1967 .

[13]  James L. McClelland.  Parallel Distributed Processing , 2005 .

[14]  Alan C. Bovik,et al.  41 OBJECTIVE VIDEO QUALITY ASSESSMENT , 2003 .

[15]  Alexander J. Smola,et al.  Learning with kernels , 1998 .

[16]  Willem Herman Steyn,et al.  Robust defocus blur identification in the context of blind image quality assessment , 2007, Signal Process. Image Commun..

[17]  A. Bovik,et al.  OBJECTIVE VIDEO QUALITY ASSESSMENT , 2003 .

[18]  Zhou Wang,et al.  Reduced-reference image quality assessment using a wavelet-domain natural image statistic model , 2005, IS&T/SPIE Electronic Imaging.

[19]  Paul S. Fisher,et al.  Image quality measures and their performance , 1995, IEEE Trans. Commun..

[20]  Alan C. Bovik,et al.  Image information and visual quality , 2006, IEEE Trans. Image Process..

[21]  Yuukou Horita,et al.  No reference image quality assessment for JPEG2000 based on spatial features , 2008, Signal Process. Image Commun..

[22]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[23]  Yuan F. Zheng,et al.  Quality Constrained Compression Using DWT-Based Image Quality Metric , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[24]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[25]  Jing Huang,et al.  Image indexing using color correlograms , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[26]  Judith Redi,et al.  Co-occurrence Matrixes for the Quality Assessment of Coded Images , 2007, 2007 IEEE International Symposium on Industrial Electronics.

[27]  Peter G. Engeldrum,et al.  Psychometric Scaling: A Toolkit for Imaging Systems Development , 2000 .

[28]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[29]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[30]  I. Chakravarti,et al.  Handbook of Methods of Applied Statistics:@@@Volume I: Techniques of Computation, Descriptive Methods, and Statistical Inference@@@Volume II: Planning of Surveys and Experiments. , 1968 .

[31]  Stefan Winkler,et al.  Issues in vision modeling for perceptual video quality assessment , 1999, Signal Process..

[32]  Alan C. Bovik,et al.  A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms , 2006, IEEE Transactions on Image Processing.

[33]  Daniele D. Giusto,et al.  A multi-factors approach for image quality assessment based on a human visual system model , 2006, Signal Process. Image Commun..

[34]  Ingrid Heynderickx,et al.  A Perceptually Relevant No-Reference Blockiness Metric Based on Local Image Characteristics , 2009, EURASIP J. Adv. Signal Process..

[35]  Zhou Wang,et al.  Quality-aware images , 2006, IEEE Transactions on Image Processing.

[36]  Vittorio Baroncini.  New Tendencies in Subjective Video Quality Evaluation , 2006, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[37]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .