Dear Milan Tripathi,

Try the method: Article Robust Structural Similarity Index Measure for Images with n...

There, you may find a solution/answer.

Dear Milan Tripathi ,

t clearly demonstrates that SSIM index values increases with the increasing value of noise amplitude and attains a peak and then it starts decreasing. SSIM index attains maximum value at noise amplitude of "4".

Article Enhancement of positron emission tomography-computed tomogra...

Regards,

Shafagat

Respected, Shafagat Mahmudova ,

In figure 4, you said processed 1 image scored maximum, but in the table score of processed 2 is higher

In figure 5, you said the processed 2 image scored maximum, but in the table score of processed 1 is higher

Is it some kind of misplacement error?

The Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) are two commonly used metrics for evaluating the quality of reconstructed or processed images.

In image processing, the sigma value is often associated with the amount of smoothing or blurring applied to an image. Increasing the sigma value leads to a higher degree of smoothing or blurring. The effect of increasing the sigma value on PSNR and SSIM can be explained as follows:

When the sigma value is increased, more smoothing or blurring is applied to the image. This blurring can cause loss of high-frequency details and fine textures in the image. As a result, the mean squared error between the original and processed images increases, leading to a decrease in PSNR. In other words, the blurring introduced by a higher sigma value results in a larger difference between the original and processed images, which lowers the PSNR value.

When the sigma value is increased, the blurring effect can help to reduce noise and enhance the overall structural similarity between the original and processed images. The blurring can smooth out noise and minor variations, making the images more similar in terms of structure. Therefore, increasing the sigma value tends to improve the SSIM value because the structural similarity is enhanced.