Algorithm for image quality measurement using singular value decomposition

In this paper we presented an algorithm for image quality measurement based on HVS properties and singular value decomposition. Both of the original and the distorted image are first pre-processed according to HVS properties and then their image matrixes are transformed into vectors by singular value decomposition. By comparing the angle between singular vectors of the original image and the distorted one, the quality of an image can be measured. The algorithm can be sensible to the perceptual error and can be implemented easily. We validated the performance of this algorithm using an extensive study involving many types of images, and the experiment result shows that it has good correlation with the subjective score.