No-Reference Image Quality Assessment Using Texture Information Banks

In this paper, we propose a new no-reference quality assessment method which uses a machine learning technique based on texture analysis. The proposed method compares test images with texture images of a public database. Local Binary Patterns (LBPs) are used as local texture feature descriptors. With a Csiszár-Morimoto divergence measure, the histograms of the LBPs of the test images are compared with the histograms of the LBPs of the database texture images, generating a set of difference measures. These difference measures are used to blindly predict the quality of an image. Experimental results show that the proposed method is fast and has a good quality prediction power, outperforming other no-reference image quality assessment methods.

[1]  Sanjit K. Mitra,et al.  No-reference video quality metric based on artifact measurements , 2005, IEEE International Conference on Image Processing 2005.

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

[3]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  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.

[5]  Simon C. K. Shiu,et al.  Effective texture classification by texton encoding induced statistical features , 2015, Pattern Recognit..

[6]  Minghui Meng,et al.  Application of Support Vector Machines to a Small-Sample Prediction , 2015 .

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

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

[9]  Hua Huang,et al.  No-reference image quality assessment based on spatial and spectral entropies , 2014, Signal Process. Image Commun..

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

[11]  Wen Gao,et al.  Progressive Image Denoising Through Hybrid Graph Laplacian Regularization: A Unified Framework , 2014, IEEE Transactions on Image Processing.

[12]  Francesca De Simone,et al.  Subjective evaluation of JPEG XR image compression , 2009, Optical Engineering + Applications.

[13]  Sergio Verdú,et al.  Upper bounds on the relative entropy and Rényi divergence as a function of total variation distance for finite alphabets , 2015, 2015 IEEE Information Theory Workshop - Fall (ITW).

[14]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[15]  D. Tax,et al.  The dissimilarity representation , a basis for a domain-based pattern recognition ? , 1990 .

[16]  Seiichi Gohshi,et al.  Subjective assessment of super-resolution , 2015, 2015 10th Asia-Pacific Symposium on Information and Telecommunication Technologies (APSITT).

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

[18]  Andrzej Cichocki,et al.  Families of Alpha- Beta- and Gamma- Divergences: Flexible and Robust Measures of Similarities , 2010, Entropy.

[19]  Min Zhang,et al.  Blind Image Quality Assessment Using the Joint Statistics of Generalized Local Binary Pattern , 2015, IEEE Signal Processing Letters.

[20]  Lucjan Janowski,et al.  Video Quality Assessment: Subjective testing of entertainment scenes , 2015, IEEE Signal Processing Magazine.

[21]  D. Chandler.  Seven Challenges in Image Quality Assessment: Past, Present, and Future Research , 2013 .

[22]  Wen Gao,et al.  SSIM-inspired divisive normalization for perceptual video coding , 2011, 2011 18th IEEE International Conference on Image Processing.

[23]  Qingjie Zhao,et al.  Blind image quality assessment by relative gradient statistics and adaboosting neural network , 2016, Signal Process. Image Commun..

[24]  Zhou Wang,et al.  Why is image quality assessment so difficult? , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[25]  Jukka Komulainen,et al.  Face anti-spoofing based on color texture analysis , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[26]  Abdelmalik Taleb-Ahmed,et al.  Face spoofing detection from single images using active shape models with Stasm and LBP , 2015 .

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

[28]  Abdelmalik Taleb-Ahmed,et al.  Gender and texture classification: A comparative analysis using 13 variants of local binary patterns , 2015, Pattern Recognit. Lett..

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

[30]  Beatriz Marcotegui,et al.  Local Blur Estimation Based on Toggle Mapping , 2015, ISMM.

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

[32]  Weisi Lin,et al.  No-reference quality assessment of deblocked images , 2016, Neurocomputing.

[33]  Wen Gao,et al.  Image Interpolation via Graph-Based Bayesian Label Propagation , 2014, IEEE Transactions on Image Processing.

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

[35]  Oksam Chae,et al.  Local Directional Number Pattern for Face Analysis: Face and Expression Recognition , 2013, IEEE Transactions on Image Processing.

[36]  Baojun Zhao,et al.  Gradient-based no-reference image blur assessment using extreme learning machine , 2016, Neurocomputing.

[37]  T. Morimoto.  Markov Processes and the H -Theorem , 1963 .