Repairing and Inpainting Damaged Images using Diffusion Tensor
This work addresses image inpainting for applications like removing scratches or text, but it appears incremental as it builds on existing diffusion-based techniques.
The paper tackles the problem of repairing damaged images by proposing a method based on a nonlinear diffusion tensor that tracks local geometry and allows diffusion only along isophotes curves, demonstrating effective performance on test and real color images.
Removing or repairing the imperfections of a digital images or videos is a very active and attractive field of research belonging to the image inpainting technique. This later has a wide range of applications, such as removing scratches in old photographic image, removing text and logos or creating cartoon and artistic effects. In this paper, we propose an efficient method to repair a damaged image based on a non linear diffusion tensor. The idea is to track perfectly the local geometry of the damaged image and allowing diffusion only in the isophotes curves direction. To illustrate the effective performance of our method, we present some experimental results on test and real photographic color images