Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Exemplar-Based Inpainting Using Shift-Map and Roof Duality

Svensson, Fredrik LU (2013) In Master's Theses in Mathematical Sciences FMA820 20131
Mathematics (Faculty of Engineering)
Abstract
To inpaint a digital image is to fill in unwanted pixels in an image with other, plausible, content. One use of this is to remove unwanted objects in a photograph. A user marks the unwanted objects, and then the objects should automatically disappear. There are many ways to inpaint images, and one of them is so called exemplar-based. This means that other parts of the image is copied into the area that should be replaced. Every pixel marked by the user is mapped to another pixel in the image, from which it copies its content.
This thesis investigates both if the optimization method can be improved and if the model describing the image can be improved compared to the state-of-the-art. The problem is modeled as a function that is to be... (More)
To inpaint a digital image is to fill in unwanted pixels in an image with other, plausible, content. One use of this is to remove unwanted objects in a photograph. A user marks the unwanted objects, and then the objects should automatically disappear. There are many ways to inpaint images, and one of them is so called exemplar-based. This means that other parts of the image is copied into the area that should be replaced. Every pixel marked by the user is mapped to another pixel in the image, from which it copies its content.
This thesis investigates both if the optimization method can be improved and if the model describing the image can be improved compared to the state-of-the-art. The problem is modeled as a function that is to be minimized. It is shown that the minimum value is lowered by applying so called roof duality, which is a discrete optimization method. Also, it is demonstrated that modifications to the model can improve the qualitative result in many ways. Those aim at removing several undesired phenomena without worsening any other results, for example badly mapped high frequency content. The modications are tested and compared on real images with good results. (Less)
Please use this url to cite or link to this publication:
author
Svensson, Fredrik LU
supervisor
organization
course
FMA820 20131
year
type
H2 - Master's Degree (Two Years)
subject
publication/series
Master's Theses in Mathematical Sciences
report number
LUTFMA-3248-2013
ISSN
1404-6342
other publication id
2013:E30
language
English
id
4113861
date added to LUP
2014-02-27 14:20:52
date last changed
2014-02-27 14:20:52
@misc{4113861,
  abstract     = {To inpaint a digital image is to fill in unwanted pixels in an image with other, plausible, content. One use of this is to remove unwanted objects in a photograph. A user marks the unwanted objects, and then the objects should automatically disappear. There are many ways to inpaint images, and one of them is so called exemplar-based. This means that other parts of the image is copied into the area that should be replaced. Every pixel marked by the user is mapped to another pixel in the image, from which it copies its content.
This thesis investigates both if the optimization method can be improved and if the model describing the image can be improved compared to the state-of-the-art. The problem is modeled as a function that is to be minimized. It is shown that the minimum value is lowered by applying so called roof duality, which is a discrete optimization method. Also, it is demonstrated that modifications to the model can improve the qualitative result in many ways. Those aim at removing several undesired phenomena without worsening any other results, for example badly mapped high frequency content. The modications are tested and compared on real images with good results.},
  author       = {Svensson, Fredrik},
  issn         = {1404-6342},
  language     = {eng},
  note         = {Student Paper},
  series       = {Master's Theses in Mathematical Sciences},
  title        = {Exemplar-Based Inpainting Using Shift-Map and Roof Duality},
  year         = {2013},
}