Exemplar based Image Inpainting with Reduced Search Region

Image inpainting is a technique to recover lost data or manually remove data from an image. This process is carried out in such a way that it seems reasonable to human eyes. The lost part of the image is filled with the remaining available data of the image. Inpainting can be done using various techniques, mainly variation based, exemplar based and wavelet based. In this paper, exemplar based image inpainting techniques is used and an algorithm which improves and extends the previously proposed algorithm is presented. Instead of searching the entire image, the proposed approach has reduced the search region by searching the nearby pixels since most of the relevant information lies in neighbouring pixels which reduces time to complete inpainting. This technique is mainly used for removing objects and cracks from the image.