This paper presents a novel method for image segmentation. We improved the effect of saliency detection for the purpose of image segmentation. Graph cuts are used to find global optimal segmentation of N-dimensional image. With the guidance of saliency, users do not have to select foreground object and background seeds. The main advantages of our method are that: Firstly we revised the existed sparse saliency model to better suit for image segmentation, Secondly we propose a new color modeling method during the process of GrabCut segmentation. Finally we combine these two processes together to segment images without interference. We demonstrate our proposed scheme for image segmentation on several databases and get satisfactory results.