Evaluation of Information ContentWeighted SSIM (IWSSIM) Lin Zhang, School of Software Engineering, Tongji University 
Introduction
Information Content Weighted SSIM (IWSSIM) index is an extension of MSSSIM by using spatially varied weights. It is presented by Dr. Zhou Wang et al. on 2011 [1].
Source Code
The authors provide their implementation, which can be downloaded here https://ece.uwaterloo.ca/~z70wang/research/iwssim/iwssim_iwpsnr.zip.
Usage Notes
1. Do not change the default parameter settings.
2. IWSSIM can only deal with grayscale images and the luminance range is [0, 255]. So, for color images, before calling IWSSIM, you need to convert it to [0, 255] grayscale version. Usually, this can be accomplished by the Matlab routine rgb2gray.
Evaluation Results
The results (in Matlab .mat format) are provided here. Each result file contains a n by 2 matrix, where n denotes the number of distorted images in the database. The first column is the IWSSIM values, and the second column is the mos/dmos values provided by the database. For example, you can use the following matlab code to calculate the SROCC and KROCC values for IWSSIM values obtained on the TID2008 database:
%%%%%%%%%%%%%%%
matData
= load('IWSSIMOnTID.mat');
IWSSIMOnTID= matData.IWSSIMOnTID;
IWSSIM_TID_SROCC = corr(IWSSIMOnTID(:,1), IWSSIMOnTID(:,2), 'type', 'spearman');
IWSSIM_TID_KROCC = corr(IWSSIMOnTID(:,1), IWSSIMOnTID(:,2), 'type', 'kendall');
%%%%%%%%%%%%%%%
The source codes to calculate the PLCC and RMSE are also provided for each database. This needs a nonlinear regression procedure which is dependant on the initialization of the parameters. We try to adjust the parameters to get a high PLCC value. For different databases, the parameter initialization may be different. The nonlinear fitting function is of the form as described in [2].
Evaluation results of IWSSIM on seven databases are given below. Besides, for each evaluation metric, we present its weightedaverage value over all the testing datasets; and the weight for each database is set as the number of distorted images in that dataset.
Database 
Results 
Nonlinear fitting code  SROCC  KROCC  PLCC  RMSE 
TID2013 
NonlinearFittingTID2013  0.7779  0.5977  0.8319  0.6880  
TID2008 
NonlinearFittingTID  0.8559  0.6636  0.8579  0.6895  
CSIQ 
NonlinearFittingCSIQ  0.9213  0.7529  0.9144  0.1063  
LIVE 
NonlinearFittingLIVE  0.9567  0.8175  0.9522  8.3473  
IVC 
NonlinearFittingIVC  0.9125  0.7339  0.9231  0.4686  
ToyamaMICT 
0.9202  0.7537  0.9248  0.4761  
A57 
0.8709  0.6842  0.9034  0.1054  
WIQ 
0.7865  0.6038  0.8329  12.6765  
WeightedAverage 

Reference
[1] Z. Wang and Q. Li, "Information content weighting for perceptual image quality assessment", IEEE Trans. on Image Processing, vol. 20, no. 5, pp. 11851198, 2011.
[2] H.R. Sheikh, M.F. Sabir, and A.C. Bovik, "A statistical evaluation of recent full reference image quality assessment algorithms", IEEE Trans. on Image Processing, vol. 15, no. 11, pp. 34403451, 2006.
Created on: May 09, 2011
Last update: Dec. 07, 2013