Object Removal and Filling by Criminisi‟s Exemplar Based Inpainting Technique

Abstract

Inpainting is the art of modifying an image in a form that is not detectable by an ordinary observer. There are numerous and different approaches to tackle the Inpainting problem. This paper demonstrates Criminisi‟s algorithm for removing large objects from digital images and filling the hole left behind. The Inpainting technique can be classified into two categories: (1) texture oriented and (2) structure oriented. Both the technique have their advantages and disadvantages. The Criminisi‟s algorithm demonstrated in this paper combines the advantages of both of these approaches. Exemplar based structure synthesis contains the essential process to replicate both texture and structure. A number of examples on real and synthetic images demonstrate the effectiveness of the algorithm.