Bibliographic citations
This is an automatically generated citacion. Modify it if you see fit
Paredes, D., (2014). Multi-scale image inpainting with label selection based on local statistics [Tesis, Pontificia Universidad Católica del Perú]. http://hdl.handle.net/20.500.12404/5578
Paredes, D., Multi-scale image inpainting with label selection based on local statistics [Tesis]. PE: Pontificia Universidad Católica del Perú; 2014. http://hdl.handle.net/20.500.12404/5578
@mastersthesis{renati/499033,
title = "Multi-scale image inpainting with label selection based on local statistics",
author = "Paredes Zevallos, Daniel Leoncio",
publisher = "Pontificia Universidad Católica del Perú",
year = "2014"
}
Title: Multi-scale image inpainting with label selection based on local statistics
Authors(s): Paredes Zevallos, Daniel Leoncio
Advisor(s): Rodríguez Valderrama, Paúl Antonio
OCDE field: https://purl.org/pe-repo/ocde/ford#2.02.05
Issue Date: 9-Sep-2014
Institution: Pontificia Universidad Católica del Perú
Abstract: 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.
Link to repository: http://hdl.handle.net/20.500.12404/5578
Discipline: Procesamiento de señales e imágenes digitales
Grade or title grantor: Pontificia Universidad Católica del Perú. Escuela de Posgrado
Grade or title: Maestro en Procesamiento de señales e imágenes digitales
Register date: 9-Sep-2014
This item is licensed under a Creative Commons License