Image Inpainting by Optimized Exemplar egion Filling Algorithm
Shivali Tyagi1, Sachin Singh2

1Shivali Tyagi, Computer Science and Engineering, SRM University, Ghaziabad, India.
2Sachin Singh, Computer Science and Engineering, SRM University, Ghaziabad, India.
Manuscript received on January 01, 2013. | Revised Manuscript received on January 02, 2013. | Manuscript published on January 05, 2013. | PP: 475-479 | Volume-2, Issue-6, January 2013. | Retrieval Number: F1194112612/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: This paper discusses removing objects from digital images and fills the hole that is left behind. Here, we present a novel and effective algorithm that combines the advantages of these two approaches. We first note that exemplar-based texture synthesis contains the essential process required to replicate both texture and structure; the success of structure propagation, however, is highly dependent on the order in which the filling proceeds. The existing algorithms are combined to improve the efficiency for finding the line association in selected region (like solid objects). Main focus is on data term and confidence term to find line association in selected region which is to be inpainted. The region filling is done from that line associated to other section in selected region.
Keywords: Confidence term, data term, exemplar-based texture, image inpainting, region based algorithm synthesis.