Return to search

Multi-scale image inpainting with label selection based on local statistics

We proposed a novel inpainting method where we use a multi-scale approach to speed
up the well-known Markov Random Field (MRF) based inpainting method. MRF based
inpainting methods are slow when compared with other exemplar-based methods, because
its computational complexity is O(jLj2) (L feasible solutions’ labels). Our multi-scale
approach seeks to reduces the number of the L (feasible) labels by an appropiate selection
of the labels using the information of the previous (low resolution) scale. For the initial
label selection we use local statistics; moreover, to compensate the loss of information in
low resolution levels we use features related to the original image gradient.
Our computational results show that our approach is competitive, in terms reconstruction
quality, when compare to the original MRF based inpainting, as well as other exemplarbased
inpaiting algorithms, while being at least one order of magnitude faster than the original
MRF based inpainting and competitive with exemplar-based inpaiting. / Tesis

Identiferoai:union.ndltd.org:PUCP/oai:tesis.pucp.edu.pe:123456789/5578
Date09 September 2014
CreatorsParedes Zevallos, Daniel Leoncio
ContributorsRodríguez Valderrama, Paúl Antonio
PublisherPontificia Universidad Católica del Perú
Source SetsPontificia Universidad Católica del Perú
LanguageEnglish
Detected LanguageEnglish
Typeinfo:eu-repo/semantics/masterThesis
Formatapplication/pdf
SourcePontificia Universidad Católica del Perú, Repositorio de Tesis - PUCP
Rightsinfo:eu-repo/semantics/openAccess, Atribución-NoComercial-SinDerivadas 2.5 Perú, http://creativecommons.org/licenses/by-nc-nd/2.5/pe/

Page generated in 0.0021 seconds