Image Quality Perception Measures

Question

I am currently working on an algorithm for image noise reduction. I need to compare my algorithm with other existing algorithms, but for this I need a quality measure.
The main goal of such a measure is to be closer to human perception skills. I know this is almost impossible, but there are good perceptual measures for audio signals. Are there similar algorithms for images?

Right now I am using simple measures such as standard error (MSE), signal to noise ratio (SNR), etc.


And for your information, I am currently implementing this in matlab

Answer 1

Have you checked SSIM ( http://en.wikipedia.org/wiki/Structural_similarity )? The following page ( http://www.ece.uwaterloo.ca/~z70wang/research/ssim/ ) gives you a real-life example of how SSIM works compared to MSE.