The aim of this study was to reduce the amount of calculation and improve the computational efficiency, and to achieve the consistency of the assessment algorithm with the human eye observation. First of all, the region of interest was extracted, and the focus, the attention time, the eyeball movement track and the saccade data of human eyes during observation of the image were recorded using an eye tracker. Then the saliency region was extracted. The region of interest was introduced into the objective visual model to evaluate image quality, and the merits of the image quality were objectively evaluated by measuring the percentages of effective perception transitions of the image, and the algorithm of this paper was compared with the traditional algorithm. The region of interest contained most of the key information of the image on which the human eyes focused. The percentages of effective perception transitions of region of interest of image based on different enhancement methods were bigger than that (20.3% ) of the original image. The algorithm proposed in this paper was superior to the traditional objective assessment algorithm and the objective quality assessment result accorded more with human visual characteristics.