No-reference image quality assessment in curvelet domain

Abstract We study the efficacy of utilizing a powerful image descriptor, the curvelet transform, to learn a no-reference (NR) image quality assessment (IQA) model. A set of statistical features are extracted from a computed image curvelet representation, including the coordinates of the maxima of the log-histograms of the curvelet coefficients values, and the energy distributions of both orientation and scale in the curvelet domain. Our results indicate that these features are sensitive to the presence and severity of image distortion. Operating within a 2-stage framework of distortion classification followed by quality assessment, we train an image distortion and quality prediction engine using a support vector machine (SVM). The resulting algorithm, dubbed CurveletQA for short, was tested on the LIVE IQA database and compared to state-of-the-art NR/FR IQA algorithms. We found that CurveletQA correlates well with human subjective opinions of image quality, delivering performance that is competitive with popular full-reference (FR) IQA algorithms such as SSIM, and with top-performing NR IQA models. At the same time, CurveletQA has a relatively low complexity.

[1]  Alan C. Bovik,et al.  No-reference image blur assessment using multiscale gradient , 2009, QOMEX 2009.

[2]  E. Candès.  New tight frames of curvelets and optimal representations of objects with C² singularities , 2002 .

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

[4]  Brian C. Lovell,et al.  Face Recognition from Still Images to Video Sequences: A Local-Feature-Based Framework , 2011, EURASIP J. Image Video Process..

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

[6]  E. Candès,et al.  New tight frames of curvelets and optimal representations of objects with piecewise C2 singularities , 2004 .

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

[8]  Christophe Charrier,et al.  A DCT Statistics-Based Blind Image Quality Index , 2010, IEEE Signal Processing Letters.

[9]  Lina J. Karam,et al.  A No-Reference Image Blur Metric Based on the Cumulative Probability of Blur Detection (CPBD) , 2011, IEEE Transactions on Image Processing.

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

[11]  Gordon Erlebacher,et al.  Hybrid No-Reference Natural Image Quality Assessment of Noisy, Blurry, JPEG2000, and JPEG Images , 2011, IEEE Transactions on Image Processing.

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

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

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

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

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

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

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

[19]  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.

[20]  Xuelong Li,et al.  Reduced-Reference IQA in Contourlet Domain , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[21]  Tiago Rosa Maria Paula Queluz,et al.  No-reference image quality assessment based on DCT domain statistics , 2008, Signal Process..

[22]  Alan C. Bovik,et al.  Motion Tuned Spatio-Temporal Quality Assessment of Natural Videos , 2010, IEEE Transactions on Image Processing.

[23]  S. Gabarda,et al.  Blind image quality assessment through anisotropy. , 2007, Journal of the Optical Society of America. A, Optics, image science, and vision.

[24]  Xuelong Li,et al.  Universal Blind Image Quality Assessment Metrics Via Natural Scene Statistics and Multiple Kernel Learning , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[25]  Xuelong Li,et al.  Image Quality Assessment Based on Multiscale Geometric Analysis , 2009, IEEE Transactions on Image Processing.

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

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

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

[29]  Laurent Demanet,et al.  Fast Discrete Curvelet Transforms , 2006, Multiscale Model. Simul..

[30]  Zhou Wang,et al.  No-reference image sharpness assessment based on local phase coherence measurement , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[31]  Xuelong Li,et al.  Sparse representation for blind image quality assessment , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.