Blind image quality assessment with improved natural scene statistics model

No-reference (NR)/blind image quality assessment (IQA) metrics play an important role in the area of image processing. Natural scene statistics (NSS) model assumes that natural images possess certain regular statistical properties and is widely used in NR IQA metrics. Most existing NSS-based NR algorithms are achieved by measuring the variation of image statistics, which are characterized by the fitting parameters of NSS model, across different distortions. However, distortions not only change the image statistics, but also disturb the statistical regularity held by natural images. As a result, the distribution of distorted images can not well follow the NSS model. There exists fitting error between the real distribution of the distorted image and the fitted one under certain NSS model. In this paper, the statistical distributions of the distorted images are discussed in detail. We suggest to take the fitting errors into account as well as the fitting parameters for feature extraction, and propose a novel NR IQA algorithm. Experimental results on several image databases demonstrate that the proposed metric performs highly consistent with human visual perception.

[1]  Weisi Lin,et al.  No-Reference Image Blur Assessment Based on Discrete Orthogonal Moments , 2016, IEEE Transactions on Cybernetics.

[2]  Martin Slanina,et al.  A Matlab-Based Tool for Video Quality Evaluation without Reference , 2014 .

[3]  David S. Doermann,et al.  Unsupervised feature learning framework for no-reference image quality assessment , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Xuelong Li,et al.  Blind Image Quality Assessment via Deep Learning , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[5]  King Ngi Ngan,et al.  Reduced-Reference Video Quality Assessment of Compressed Video Sequences , 2012, IEEE Transactions on Circuits and Systems for Video Technology.

[6]  Alan C. Bovik,et al.  A Two-Step Framework for Constructing Blind Image Quality Indices , 2010, IEEE Signal Processing Letters.

[7]  Bryan Dodson,et al.  The Weibull Analysis Handbook , 1994 .

[8]  Nikolay N. Ponomarenko,et al.  TID2008 – A database for evaluation of full-reference visual quality assessment metrics , 2004 .

[9]  David S. Doermann,et al.  No-Reference Image Quality Assessment Using Visual Codebooks , 2012, IEEE Transactions on Image Processing.

[10]  Salvatore Tabbone,et al.  Asymmetric Generalized Gaussian Mixture Models and EM Algorithm for Image Segmentation , 2010, 2010 20th International Conference on Pattern Recognition.

[11]  Fan Zhang,et al.  Reduced-Reference Image Quality Assessment Using Reorganized DCT-Based Image Representation , 2011, IEEE Transactions on Multimedia.

[12]  Necip Doganaksoy,et al.  Weibull Models , 2004, Technometrics.

[13]  Gaobo Yang,et al.  Referenceless Measure of Blocking Artifacts by Tchebichef Kernel Analysis , 2014, IEEE Signal Processing Letters.

[14]  Yi Li,et al.  Convolutional Neural Networks for No-Reference Image Quality Assessment , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

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

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

[17]  Lei Zhang,et al.  A Feature-Enriched Completely Blind Image Quality Evaluator , 2015, IEEE Transactions on Image Processing.

[18]  William Bialek,et al.  Statistics of Natural Images: Scaling in the Woods , 1993, NIPS.

[19]  Weisi Lin,et al.  Perceptual visual quality metrics: A survey , 2011, J. Vis. Commun. Image Represent..

[20]  Martin Slanina,et al.  A comparison of single and double stimulus subjective assessment of full HD video sequences , 2014, 2014 24th International Conference Radioelektronika.

[21]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[22]  Guangming Shi,et al.  Reduced-reference image quality assessment based on entropy differences in DCT domain , 2015, 2015 IEEE International Symposium on Circuits and Systems (ISCAS).

[23]  Alan C. Bovik,et al.  Blind Image Quality Assessment: From Natural Scene Statistics to Perceptual Quality , 2011, IEEE Transactions on Image Processing.

[24]  Christophe Charrier,et al.  Blind Image Quality Assessment: A Natural Scene Statistics Approach in the DCT Domain , 2012, IEEE Transactions on Image Processing.

[25]  Alberto Leon-Garcia,et al.  Estimation of shape parameter for generalized Gaussian distributions in subband decompositions of video , 1995, IEEE Trans. Circuits Syst. Video Technol..

[26]  Guangming Shi,et al.  Reduced-Reference Image Quality Assessment With Visual Information Fidelity , 2013, IEEE Transactions on Multimedia.

[27]  Hua Huang,et al.  No-reference image quality assessment in curvelet domain , 2014, Signal Process. Image Commun..

[28]  Fan Zhang,et al.  Image Quality Assessment by Separately Evaluating Detail Losses and Additive Impairments , 2011, IEEE Transactions on Multimedia.

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

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

[31]  Eero P. Simoncelli,et al.  Natural image statistics and neural representation. , 2001, Annual review of neuroscience.

[32]  Guangming Shi,et al.  Perceptual Quality Metric With Internal Generative Mechanism , 2013, IEEE Transactions on Image Processing.

[33]  Xiaojun Wu,et al.  Blind Image Quality Assessment Using a General Regression Neural Network , 2011, IEEE Transactions on Neural Networks.

[34]  Alan C. Bovik,et al.  Making a “Completely Blind” Image Quality Analyzer , 2013, IEEE Signal Processing Letters.

[35]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[36]  Zhiguo Jiang,et al.  No Reference Quality Assessment for Multiply-Distorted Images Based on an Improved Bag-of-Words Model , 2015, IEEE Signal Processing Letters.

[37]  Qing Wang,et al.  A new blind image quality framework based on natural color statistic , 2016, Neurocomputing.

[38]  D. Ruderman.  The statistics of natural images , 1994 .

[39]  Damon M. Chandler,et al.  No-Reference Quality Assessment of JPEG Images via a Quality Relevance Map , 2014, IEEE Signal Processing Letters.

[40]  D J Field,et al.  Relations between the statistics of natural images and the response properties of cortical cells. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[41]  Krista A. Ehinger,et al.  SUN database: Large-scale scene recognition from abbey to zoo , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[42]  Ling Shao,et al.  Non-distortion-specific no-reference image quality assessment: A survey , 2015, Inf. Sci..

[43]  Zhou Wang,et al.  No-Reference Quality Assessment of Contrast-Distorted Images Based on Natural Scene Statistics , 2015, IEEE Signal Processing Letters.

[44]  Wenjun Zhang,et al.  Using Free Energy Principle For Blind Image Quality Assessment , 2015, IEEE Transactions on Multimedia.

[45]  Alan C. Bovik,et al.  No-Reference Image Quality Assessment in the Spatial Domain , 2012, IEEE Transactions on Image Processing.