Digital Image Inpainting: a Survey

Image inpainting also referred to as image restoration or completion is a technique used to fill-in the missing region or damaged region of an image by using the known information of an image. There are different approaches for image inpainting. First approach is diffusion based approach in which the target or missing region is filled in by diffusing the image information from the source region into the target region at the pixel level. For this it uses partial differential equations or total-variational approach. The second approach is the exemplar-based inpainting algorithm. Exemplar-based approach propagates the image information from the source or known region into the target or missing region at the patch level. This idea comes from the texture synthesis technique, in which the texture is synthesized by sampling the best match patch from the source region. Applications of this technique include the restoration of old photographs and damaged film; removal of superimposed text like dates, subtitles, or publicity; and the removal of entire objects from the image to give special effects.