A novel entropy-based texture inpainting algorithm

Abstract

Image inpainting is the process of restoring a lost or damaged portion of an image. Inpainting of an image that contains texture remains a particularly challenging problem. We aim to propose an algorithm to inpaint a textured image accurately using a single image. The main idea is to segment the given image, based on its texture. In this work, we propose a novel local energy approach, in combination with the k-means algorithm to segment the given image, based on its texture. We use this segmentation result to restrict the search of matching pixels to only-relevant segments. Moreover, we use the entropy-based dissimilarity parameter to find matching pixels, instead of the $$\ell ^2$$ distance. The restriction of the search area improves the efficiency, and the use of the proposed dissimilarity parameter provides a better way to compare textures, giving improved inpainting for textured images.