Introduction

Multiscale-SSIM (MS-SSIM) index is an extension of SSIM. It performs much better than its single-scale counterpart. It is presented by Dr. Zhou Wang et al. on 2004 [1].

Source Code

There are different implementations for MS-SSIM. In our previous papers, we used the version provided in the package MeTriX MuX. MeTriX MuX was also adopted to evaluate IQA metrics by the TID2008 creators. LIVE team also provides their version. However, these two versions are both slightly different from Dr. Zhou Wang's implementation. To make the evaluations consistent with Dr. Wang, we now use his implementation which can be downloaded here https://ece.uwaterloo.ca/~z70wang/research/iwssim/msssim.zip.

Usage Notes

1. Do not change the default parameter settings.

2. MS-SSIM can only deal with gray-scale images and the luminance range is [0, 255]. So, for color images, before calling MS-SSIM, you need to convert it to [0, 255] gray-scale 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 MS-SSIM 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 MS-SSIM values obtained on the TID2008 database:

%%%%%%%%%%%%%%%

matData = load('MSSSIMOnTID.mat');
MSSSIMOnTID = matData.MSSSIMOnTID;
MSSSIM_TID_SROCC = corr(MSSSIMOnTID(:,1), MSSSIMOnTID(:,2), 'type', 'spearman');
MSSSIM_TID_KROCC = corr(MSSSIMOnTID(:,1), MSSSIMOnTID(:,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 MS-SSIM on seven databases are given below. Besides, for each evaluation metric, we present its weighted-average value over all the testing datasets; and the weight for each database is set as the number of distorted images in that dataset.

Reference                

[1] Z. Wang, E.P. Simoncelli, and A. C. Bovik, "Multi-scale structural similarity for image quality assessment", IEEE Asilomar Conf. Signals, Systems, and Computers, pp. 1398-1402, 2003.

[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. 3440-3451, 2006.

Created on: May 08, 2011

Last update: Dec. 02, 2013