Object removal by region based filling inpainting

Abstract

Nowadays, an important part of scientific and artistic works is stored in form of film and image archive, so image processing becomes a very important task. A new topic in image processing is image inpainting. Image inpainting is filling in damaged or missed regions in an image in an undetectable form. It has several applications such as image reconstructing, video restoration, special effects and so on. A new algorithm is proposed in this Paper for removing large objects from digital images. The challenge is to fill in the hole that is left behind in a visually plausible way. We propose a best-first algorithm in which the confidence in the synthesized pixel values is propagated in a manner similar to the propagation of information in inpainting. The actual colour values are computed using exemplar-based synthesis. Computational efficiency is achieved by a block based sampling process. A number of examples on real and synthetic images demonstrate the effectiveness of our algorithm in removing large occluding objects. Our results compare favorably to those obtained by existing techniques.