Perceptually based image comparison
D. Tompa, John Baird Morton, Ed Jernigan · 2002
This paper presents a new method for measuring the difference between a distorted image and its original. Many areas of image processing require the ability to compare such images in order to evaluate the performance of a given algorithm. These areas include image restoration and image compression. The standard method currently used is the mean squared error (MSE). It is a simple value to calculate, but in many instances it provides an inaccurate representation of the image's quality. The new metrics described here provide a quantitative measure that more closely corresponds to a subjective assessment.