No reference image quality classification for JPEG-distorted images

Abstract In this paper, we address the Image Quality Assessment (IQA) of JPEG-distorted images. We approach the IQA field by focusing on a classification problem that maps different objective metrics into different categorical quality classes. To this end, we adopt a machine learning classification approach, where No Reference (NR) metrics are considered as features, while the assigned classes come from psycho-visual experiments. Eleven NR metrics have been considered: seven specific for blockiness and four general purpose. We evaluate the performance of single metrics and investigate if a pool of metrics can reach better performances than each of the single ones. Five as well as three quality classes are considered, and the corresponding classifiers are tested on two well known databases available in the literature (LIVE and MICT), and on a new database (IVL) presented in this paper.

[1]  Raimondo Schettini,et al.  Grouping strategies to improve the correlation between subjective and objective image quality data , 2013, Electronic Imaging.

[2]  Stefan Winkler,et al.  Analysis of Public Image and Video Databases for Quality Assessment , 2012, IEEE Journal of Selected Topics in Signal Processing.

[3]  Yang Hu,et al.  Machine Learning to Design Full-reference Image Quality Assessment Algorithm , 2013 .

[4]  Yuukou Horita,et al.  Impact of subjective dataset on the performance of image quality metrics , 2008, 2008 15th IEEE International Conference on Image Processing.

[5]  Weisi Lin,et al.  Scalable image quality assessment with 2D mel-cepstrum and machine learning approach , 2012, Pattern Recognit..

[6]  Eero P. Simoncelli,et al.  On Advances in Statistical Modeling of Natural Images , 2004, Journal of Mathematical Imaging and Vision.

[7]  Damon M. Chandler,et al.  Seven challenges for image quality research , 2014, Electronic Imaging.

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

[9]  Stephen A. Dyer,et al.  Digital signal processing , 2018, 8th International Multitopic Conference, 2004. Proceedings of INMIC 2004..

[10]  Khaled S. Ahmed,et al.  Estimating Protein Functions Correlation Based on Overlapping Proteins and Cluster Interactions , 2012 .

[11]  Wei-Ying Ma,et al.  Learning No-Reference Quality Metric by Examples , 2005, 11th International Multimedia Modelling Conference.

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

[13]  Ihor O. Kirenko,et al.  A no-reference blocking artifact measure for adaptive video processing , 2005, 2005 13th European Signal Processing Conference.

[14]  P. Gastaldo,et al.  MACHINE LEARNING SOLUTIONS FOR OBJECTIVE VISUAL QUALITY ASSESSMENT , 2011 .

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

[16]  Jeffrey A. Bloom,et al.  A Blind Reference-Free Blockiness Measure , 2010, PCM.

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

[18]  Sophie Triantaphillidou,et al.  Image quality comparison between JPEG and JPEG2000. I. Psychophysical investigation , 2007 .

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

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

[21]  Christophe Charrier,et al.  Machine learning to design full-reference image quality assessment algorithm , 2012, Signal Process. Image Commun..

[22]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[23]  Joyce E. Farrell,et al.  Handbook of Image Quality: Characterization and Prediction , 2004 .

[24]  T. Vlachos,et al.  Detection of blocking artifacts in compressed video , 2000 .

[25]  Judith Redi,et al.  How to apply spatial saliency into objective metrics for JPEG compressed images? , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

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

[27]  Weisi Lin,et al.  A locally-adaptive algorithm for measuring blocking artifacts in images and videos , 2004, 2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No.04CH37512).

[28]  Raimondo Schettini,et al.  A hierarchical classification strategy for digital documents , 2002, Pattern Recognit..

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

[30]  Weisi Lin,et al.  Objective Image Quality Assessment Based on Support Vector Regression , 2010, IEEE Transactions on Neural Networks.

[32]  Patrick Le Callet,et al.  Subjective quality assessment IRCCyN/IVC database , 2004 .

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

[34]  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.

[35]  Raimondo Schettini,et al.  Automatic Classification Of Digital Photographs Based On Decision Forests , 2004, Int. J. Pattern Recognit. Artif. Intell..

[36]  R. Venkatesh Babu,et al.  No-reference image quality assessment using modified extreme learning machine classifier , 2009, Appl. Soft Comput..

[37]  Raimondo Schettini,et al.  Image quality assessment by preprocessing and full reference model combination , 2009, Electronic Imaging.

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

[39]  Alan C. Bovik,et al.  Visual quality assessment algorithms: what does the future hold? , 2010, Multimedia Tools and Applications.

[40]  Zhou Wang,et al.  Blind measurement of blocking artifacts in images , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[41]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[42]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[43]  Yuukou Horita,et al.  No-Reference Image Quality Evaluation Model for JPEG and JPEG2000 Images , 2008 .

[44]  Weisi Lin,et al.  Image Quality Assessment Using Multi-Method Fusion , 2013, IEEE Transactions on Image Processing.

[45]  Eric C. Larson,et al.  Most apparent distortion: full-reference image quality assessment and the role of strategy , 2010, J. Electronic Imaging.

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

[47]  R. Put,et al.  The use of CART and multivariate regression trees for supervised and unsupervised feature selection , 2005 .

[48]  Ingrid Heynderickx,et al.  How Does Image Content Affect the Added Value of Visual Attention in Objective Image Quality Assessment? , 2013, IEEE Signal Processing Letters.

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

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

[51]  Raimondo Schettini,et al.  No-reference metrics for JPEG: analysis and refinement using wavelets , 2010, Electronic Imaging.

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