In order to evaluate and design the stitching algorithm better, a color-corrected stitched image quality assessment method is proposed. A stitched image database with five kinds of color differences is established by using the current color correction algorithm and stitching algorithm. To evaluate color-difference stitched images quality comprehensively, four features are extracted from pre-splicing image sequence and stitched image respectively. Then four features are combined to establish a relation model between features and quality through support vector regression algorithm, so as to predict color-difference stitched image quality. Experimental result shows that the proposed method can effectively evaluate color-difference stitched images quality.