A GMM-based stair quality model for human perceived JPEG images

Based on the notion of just noticeable differences (JND), a stair quality function (SQF) was recently proposed to model human perception on JPEG images. Furthermore, a k-means clustering algorithm was adopted to aggregate JND data collected from multiple subjects to generate a single SQF. In this work, we propose a new method to derive the SQF using the Gaussian Mixture Model (GMM). The newly derived SQF can be interpreted as a way to characterize the mean viewer experience. Furthermore, it has a lower information criterion (BIC) value than the previous one, indicating that it offers a better model. A specific example is given to demonstrate the advantages of the new approach.

[1]  References , 1971 .

[2]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[3]  D. Findley Counterexamples to parsimony and BIC , 1991 .

[4]  C.-C. Jay Kuo,et al.  A Haar Wavelet Approach to Compressed Image Quality Measurement , 2000, J. Vis. Commun. Image Represent..

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

[6]  Sheila S. Hemami,et al.  A scalable wavelet-based video distortion metric and applications , 2006, IEEE Transactions on Circuits and Systems for Video Technology.

[7]  Sheila S. Hemami,et al.  VSNR: A Wavelet-Based Visual Signal-to-Noise Ratio for Natural Images , 2007, IEEE Transactions on Image Processing.

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

[9]  C.-C. Jay Kuo,et al.  Compressed image quality metric based on perceptually weighted distortion , 2015, IEEE Transactions on Image Processing.

[10]  C.-C. Jay Kuo,et al.  Experimental design and analysis of JND test on coded image/video , 2015, SPIE Optical Engineering + Applications.