File(s) not publicly available
Image inpainting based on local optimisation
conference contribution
posted on 2010-11-18, 00:00 authored by J Zhou, Antonio Robles-KellyAntonio Robles-KellyIn this paper, we tackle the problem of image inpainting which aims at removing objects from an image or repairing damaged pictures by replacing the missing regions using the information in the rest of the scene. The image inpainting method proposed here builds on an exemplar-based perspective so as to improve the local consistency of the inpainted region. This is done by selecting the optimal patch which maximises the local consistency with respect to abutting candidate patches. The similarity computation generates weights based upon an edge prior and the structural differences between inpainting exemplar candidates. This treatment permits the generation of an inpainting sequence based on a list of factors. The experiments show that the proposed method delivers a margin of improvement as compared to alternative methods. © 2010 IEEE.
History
Pagination
4440 - 4443Publisher DOI
ISSN
1051-4651ISBN-13
9780769541099Publication classification
E1.1 Full written paper - refereedTitle of proceedings
Proceedings - International Conference on Pattern RecognitionUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC