Neural networks for the no-reference assessment of perceived quality

Imaging algorithms often require reliable methods to evaluate the quality effects of the visual artifacts that digital processing brings about. We adopt a no-reference objective method for predicting the perceived quality of images in a deterministic fashion. JPEG coding provides a significant and interesting case study. To enhance the coherence of the quality estimates with respect to the empirical evidence of the perceptual phenomenon, the system parameters are adjusted using subjective scores obtained from human assessors. Principal component analysis is first used to assemble a set of objective features that best characterize the information in image data. Then a neural network, based on the circular backpropagation (CBP) model, associates the selected features with the corresponding predictions of quality ratings and reproduces the scores process of human assessors. The neural model enables one to decouple the process of feature selection from the task of mapping features into a quality score. Results on a public database for an image-quality experiment involving JPEG-compressed images and comparisons with existing objective methods confirm the approach effectiveness.

[1]  H.R. Wu,et al.  A generalized block-edge impairment metric for video coding , 1997, IEEE Signal Processing Letters.

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

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

[4]  Yong Liu,et al.  Unbiased estimate of generalization error and model selection in neural network , 1995, Neural Networks.

[5]  Wilson S. Geisler,et al.  Image quality assessment based on a degradation model , 2000, IEEE Trans. Image Process..

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

[7]  Nick G. Kingsbury,et al.  A distortion measure for blocking artifacts in images based on human visual sensitivity , 1995, IEEE Trans. Image Process..

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

[9]  Jean-Philippe Bouchaud,et al.  The skewed multifractal random walk with applications to option smiles , 2002, cond-mat/0204047.

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

[11]  Zheru Chi,et al.  Image coding quality assessment using fuzzy integrals with a three-component image model , 2004, IEEE Transactions on Fuzzy Systems.

[12]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[13]  Jean-Bernard Martens,et al.  Image dissimilarity , 1998, Signal Process..

[14]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[15]  A. K. Rigler,et al.  Accelerating the convergence of the back-propagation method , 1988, Biological Cybernetics.

[16]  Peter Goldsmith,et al.  Modeling and validation of a psychovisually based image quality evaluator for DCT-based compression , 2002, Signal Process. Image Commun..

[17]  Philipp Slusallek,et al.  Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.

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

[19]  Harley R. Myler,et al.  Gabor difference analysis of digital video quality , 2004, IEEE Transactions on Broadcasting.

[20]  Marc Gazalet,et al.  Univariant assessment of the quality of images , 2002, J. Electronic Imaging.

[21]  Abdelhakim Saadane,et al.  Coded image quality assessment based on a new contrast masking model , 2004, J. Electronic Imaging.

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

[23]  Bernard Widrow,et al.  30 years of adaptive neural networks: perceptron, Madaline, and backpropagation , 1990, Proc. IEEE.

[24]  Ian T. Jolliffe,et al.  Discarding Variables in a Principal Component Analysis. I: Artificial Data , 1972 .

[25]  V. Ralph Algazi,et al.  Objective picture quality scale (PQS) for image coding , 1998, IEEE Trans. Commun..

[26]  Hazem Al-Otum.  Qualitative and quantitative image quality assessment of vector quantization, JPEG, and JPEG2000 compressed images , 2003, J. Electronic Imaging.

[27]  David Haussler,et al.  What Size Net Gives Valid Generalization? , 1989, Neural Computation.

[28]  I. Jolliffe.  Principal Component Analysis , 2002 .

[29]  Jeffrey Lubin,et al.  The use of psychophysical data and models in the analysis of display system performance , 1993 .

[30]  Huib de Ridder,et al.  Cognitive issues in image quality measurement , 2001, J. Electronic Imaging.

[31]  Lutz Prechelt,et al.  Automatic early stopping using cross validation: quantifying the criteria , 1998, Neural Networks.

[32]  W. Krzanowski.  Selection of Variables to Preserve Multivariate Data Structure, Using Principal Components , 1987 .

[33]  Jean-Bernard Martens,et al.  A single-ended blockiness measure for JPEG-coded images , 2002, Signal Process..

[34]  A. Bovik,et al.  A universal image quality index , 2002, IEEE Signal Processing Letters.

[35]  Scott J. Daly,et al.  Visible differences predictor: an algorithm for the assessment of image fidelity , 1992, Electronic Imaging.

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

[37]  Sandro Ridella,et al.  Empirical measure of multiclass generalization performance: the K-winner machine case , 2001, IEEE Trans. Neural Networks.

[38]  Jean-Bernard Martens.  Image Technology Design: A Perceptual Approach , 2003 .

[39]  Paolo Gastaldo,et al.  Objective assessment of MPEG-2 video quality , 2002, J. Electronic Imaging.

[40]  Jan P. Allebach,et al.  Human vision and electronic imaging , 1996, J. Electronic Imaging.

[41]  C.-C. Jay Kuo,et al.  A Haar Wavelet Approach to Compressed Image Quality Measurement , 2000, J. Vis. Commun. Image Represent..

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

[43]  Sandro Ridella,et al.  K-winner machines for pattern classification , 2001, IEEE Trans. Neural Networks.

[44]  Rodolfo Zunino,et al.  A multiprocessor-oriented visual tracking system , 1999, IEEE Trans. Ind. Electron..

[45]  I. Jolliffe.  Discarding Variables in a Principal Component Analysis. Ii: Real Data , 1973 .

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

[47]  Zhou Wang,et al.  Image Quality Assessment: From Error Measurement to Structural Similarity , 2004 .

[48]  Andrew P. Bradley,et al.  Perceptual quality metrics applied to still image compression , 1998, Signal Process..

[49]  Gregory Taylor,et al.  Hospital readmissions for asthma in children and young adults in Canada , 2003, Pediatric pulmonology.

[50]  M. Perrone.  Improving regression estimation: Averaging methods for variance reduction with extensions to general convex measure optimization , 1993 .

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

[52]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[53]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

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

[55]  Weisi Lin,et al.  A locally adaptive algorithm for measuring blocking artifacts in images and videos , 2004, Signal Process. Image Commun..

[56]  Alan C. Bovik,et al.  Image quality assessment using natural scene statistics , 2004 .

[57]  Deepak S. Turaga,et al.  No reference PSNR estimation for compressed pictures , 2004, Signal Process. Image Commun..

[58]  Jean-Bernard Martens,et al.  Multidimensional modeling of image quality , 2002, Proc. IEEE.

[59]  Paolo Gastaldo,et al.  CBP neural network for objective assessment of image quality , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..