Improved image inpainting exemplar-based algorithms by boundary priori-knowledge

Image inpainting plays an important role in restoration of cultural relics, pictures beautification. Criminisi algorithm creates good results large-area inpainting. However, it does still have some deficiencies such as over-extending. In this paper, two improved algorithms based on prior knowledge the boundary had been proposed by simulating idea manual repairing. An algorithm, strategy that next inpainted pixel will be near to one, named nearer neighbor first can void random bounding to-be-inpainted pixle. Another process, no-inpainted multiple directions, process a single direction. The reveal neighborhood-first performs better than Criminsi repairing missing structure while unrepaired-first texture .