Title :
Image inpainting via isophotes propagation
Author :
Benzarti, Faouzi ; Amiri, Hamid
Author_Institution :
Signal, Image & Patterns Recognition Lab. (TSIRF), ENIT, Ariana, Tunisia
Abstract :
The inpainting is a process that restore or repair a damaged or corrupted part of the image or video in undetectable form. This technique 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 a new approach for image inpainting based on non linear diffusion tensor. The idea is to track perfectly the local geometry of the damaged image and allowing diffusion only in the isophote curves direction. To illustrate the effective performance of our model, we present some experimental results on a test and real photographic color images.
Keywords :
image colour analysis; image restoration; tensors; image inpainting process; image restoration; isophote curve direction; isophotes propagation; nonlinear diffusion tensor; photographic color images; Anisotropic magnetoresistance; Equations; Image restoration; Mathematical model; Streaming media; TV; Tensile stress; Diffusion tensor; Image restoration; Inpainting; Isophote; PDE;
Conference_Titel :
Sciences of Electronics, Technologies of Information and Telecommunications (SETIT), 2012 6th International Conference on
Conference_Location :
Sousse
Print_ISBN :
978-1-4673-1657-6
DOI :
10.1109/SETIT.2012.6481941