Image quality assessment based on multi-scale representation of structure

This paper presents an image quality assessment algorithm using representation of image structures in scale space. It is based on the finding that difference-of-Gaussian (DoG) can capture the structures of an image with flexibility and it is sensitive to image degradations. A set of DoG signals are first computed to represent the image structures at different octaves and scales. A coarse quality score is calculated by comparing the DoG signals between the reference image and test image at each octave and scale. Information content weighting is then incorporated to generate the final quality score. Experimental results on five singly-distorted databases and the Laboratory for Image and Video Engineering (LIVE) multiply-distorted database show the effectiveness of the proposed method.