DIGITAL INPAINTING BASED IMAGE RESTORATION

Abstract

Inpainting is an image interpolation problem with broad applications in image and vision analysis. Digital inpainting is related to automatic filling-in of user-selected regions in digital images. It refers to removal of image defects such as scratches and blotches as well as removal of disturbing objects as, for instance, subtitles, logos, dates etc., and restoring the same with information surrounding them, so that it blend seamlessly with rest of the image. An extensive survey of previous work related to the digital inpainting is presented to fill in the gap and a new algorithm is proposed, which is motivated by the quality of results, easier implementation, efficiency, and effectiveness. The restored images obtained with this algorithm look plausible in general and surprisingly good in some cases. In addition, it is also having edge over other algorithms in terms of computation time and image quality while filling-in large region.