Gradient and luminance similarity based image quality metric

The aim of the objective image quality assessment is to evaluate the quality of a degraded image sensed by human visual system. This paper proposes a full-reference image quality assessment scheme using gradient and luminance similarity. Gradients gives significant visual data and important to understand the contents. Therefore, the gradient distortion is measured. In addition, image quality is also influenced by luminance changes. So, proposed method uses the singular values to obtain the luminance similarity map, since the singular values are related to the luminance changes in images. At last, the effects of the changes in gradient and luminance are pooled via an adaptive method to obtain the overall image quality score. Experimental results show that the proposed method improves accuracy and robustness of image quality prediction.