Image inpainting is an important research field in the area of image restoration

which can be used to restore damaged images and videos

remove text and conceal errors in videos. Now many inpainting algorithms perform well in the gray image inpainting

but they are time consuming and not quite applicable to color images. This paper introduces coherence-enhancing diffusion into image inpainting

and adapts it to improve the efficiency and performance of inpainting. Moreover our method can extend for color image inpainting naturally. Many experimental results prove our method is effective.