Region saliency has not been fully considered in most previous image quality assessment models. In this article, the contribution of any region to the global quality measure of an image is weighted with variable weights computed as a function of its saliency. In salient regions, the differences between distorted and original images are emphasized as if the authors are observing the difference image with a magnifying glass. Here a mixed saliency map model based on Itti's model and face detection is proposed. Both low-level features including intensity, color, orientation, and high-level features such as face are used in the mixed model. Differences in salient regions are then given more importance and thus contribute more to the image quality score. The experiments done on the 1700 distorted images of the TID2008 database show that the performance of the image quality assessment on full subsets is enhanced.