Efficient neural-network-based no-reference approach to an overall quality metric for JPEG and JPEG2000 compressed images

Reliably assessing overall quality of JPEG/JPEG2000 coded images without having the original image as a reference is still challenging, mainly due to our limited understanding of how humans combine the various perceived artifacts to an overall quality judgment. A known approach to avoid the explicit simulation of human assessment of overall quality is the use of a neural network. Neural network approaches usually start by selecting active features from a set of generic image characteristics, a process that is, to some extent, rather ad hoc and computationally extensive. This paper shows that the complexity of the feature selection procedure can be considerably reduced by using dedicated features that describe a given artifact. The adaptive neural network is then used to learn the highly nonlinear relationship between the features describing an artifact and the overall quality rating. Experimental results show that the simplified feature selection procedure, in combination with the neural network, indeed are able to accurately predict perceived image quality of JPEG/JPEG2000 coded images.

[1]  Huib de Ridder,et al.  Percentage scaling: a new method for evaluating multiply impaired images , 2000, Electronic Imaging.

[2]  Alan C. Bovik,et al.  Image information and visual quality , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  Ingrid Heynderickx,et al.  Perceivable artifacts in compressed video and their relation to video quality , 2009, Signal Process. Image Commun..

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

[5]  Stefan Winkler,et al.  A no-reference perceptual blur metric , 2002, Proceedings. International Conference on Image Processing.

[6]  Paolo Gastaldo,et al.  Objective quality assessment of MPEG-2 video streams by using CBP neural networks , 2002, IEEE Trans. Neural Networks.

[7]  Stefan Winkler,et al.  Vision models and quality metrics for image processing applications , 2001 .

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

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

[10]  Ling Shao,et al.  Coding Artifact Reduction using Non-Reference Block Grid Visibility Measure , 2006, 2006 IEEE International Conference on Multimedia and Expo.

[11]  Paolo Gastaldo,et al.  Neural networks for the no-reference assessment of perceived quality , 2005, J. Electronic Imaging.

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

[13]  Ian R. L. Davies,et al.  Automated image quality assessment , 1993, Electronic Imaging.

[14]  Zhou Wang,et al.  Modern Image Quality Assessment , 2006, Modern Image Quality Assessment.

[15]  Alan C. Bovik,et al.  Mean squared error: Love it or leave it? A new look at Signal Fidelity Measures , 2009, IEEE Signal Processing Magazine.

[16]  Ingrid Heynderickx,et al.  Objective quality assessment of displayed images by using neural networks , 2005, Signal Process. Image Commun..

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

[18]  Russell M. Mersereau,et al.  A constant subjective quality MPEG encoder , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

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

[20]  Sanjit K. Mitra,et al.  Annoyance of individual artifacts in MPEG-2 compressed video and their relation to overall annoyance , 2005, IS&T/SPIE Electronic Imaging.

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

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

[23]  Zhou Wang,et al.  Reduced-Reference Image Quality Assessment Using Divisive Normalization-Based Image Representation , 2009, IEEE Journal of Selected Topics in Signal Processing.

[24]  Judith Redi,et al.  Comparing subjective image quality measurement methods for the creation of public databases , 2010, Electronic Imaging.

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

[26]  K. van Zon,et al.  Automated video chain optimization , 2001, ICCE 2001.

[27]  Nikolay N. Ponomarenko,et al.  METRICS PERFORMANCE COMPARISON FOR COLOR IMAGE DATABASE , 2008 .

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

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

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

[31]  J A Solomon,et al.  Model of visual contrast gain control and pattern masking. , 1997, Journal of the Optical Society of America. A, Optics, image science, and vision.

[32]  Jan P. Allebach,et al.  Measurement of ringing artifacts in JPEG images , 2006, Electronic Imaging.

[33]  Judith Redi,et al.  No-reference image quality assessment based on localized gradient statistics: application to JPEG and JPEG2000 , 2010, Electronic Imaging.

[34]  Ingrid Heynderickx,et al.  A Perceptually Relevant Approach to Ringing Region Detection , 2010, IEEE Transactions on Image Processing.

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

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

[37]  Sanjit K. Mitra,et al.  Perceptual contributions of blocky, blurry, and fuzzy impairments to overall annoyance , 2004, IS&T/SPIE Electronic Imaging.

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

[39]  Ingrid Heynderickx,et al.  A No-Reference Metric for Perceived Ringing Artifacts in Images , 2010, IEEE Transactions on Circuits and Systems for Video Technology.

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

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

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

[43]  Michael Yuen,et al.  A survey of hybrid MC/DPCM/DCT video coding distortions , 1998, Signal Process..

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

[45]  Lina J. Karam,et al.  A No-Reference Objective Image Sharpness Metric Based on the Notion of Just Noticeable Blur (JNB) , 2009, IEEE Transactions on Image Processing.

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

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

[48]  Judith Redi,et al.  Color Distribution Information for the Reduced-Reference Assessment of Perceived Image Quality , 2010, IEEE Transactions on Circuits and Systems for Video Technology.

[49]  Andrew Perkis,et al.  No-reference JPEG-image quality assessment using GAP-RBF , 2007, Signal Process..

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

[51]  Tubagus Maulana Kusuma,et al.  Reduced-reference metric design for objective perceptual quality assessment in wireless imaging , 2009, Signal Process. Image Commun..