Dear Sir. Concerning your issue about the interpret the results of PSNR and MSE for the quality evaluation of images. The mean squared error (MSE) and its related metrics such as peak signal to noise ratio (PSNR), root mean squared error (RMSE) and signal to noise ratio (SNR) have been the basis for mathematically defined image quality measurement for a long time. These methods are all based on the MSE. Denoised image quality has also been traditionally measured in terms of the MSE or its derivatives. However, none of these metrics takes the structural fidelity of the image into account. We investigate the structural changes that occur during the denoising process and attempt to study an alternative metric for determining the quality of denoised images based on structural changes. I think the following below links may help you in your analysis:

http://www.naun.org/main/NAUN/circuitssystemssignal/20-611.pdf

http://www.ni.com/white-paper/13306/en/

https://pdfs.semanticscholar.org/cfab/5b500506078117125146c0d283d2392ff2e3.pdf

http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.219.5535&rep=rep1&type=pdf

Thanks

Thank you. What about quality evaluation of segmented images?

Sorry,

Do not know.