Abstrait

Comparative Analysis of Fragment based and Exemplar based Inpainting Techniques

J. N. Kazi , Y.M. Patil

Inpainting is an art of modifying the digital image in such a way that the modifications/alterations are undetectable to an observer who is unknown of the original image. Applications of this technique include restoration of damaged photographs & films, removal of superimposed text, removal/replacement of unwanted objects. After the user selects a region to be inpainted the algorithm automatically fills in these holes by data sampled from remainder of the image. In past the problem of inpainting was addressed by two classes of algorithms (i) “diffusion based inpainting” and (ii) “texture synthesis”. Further extensive research has undergone in this field which resulted in variety of inpainting techniques. In this paper we will compare Fragment based [2] and Exemplar based [1] inpainting techniques.

Avertissement: Ce résumé a été traduit à l'aide d'outils d'intelligence artificielle et n'a pas encore été examiné ni vérifié