Advanced

Regularizing Image Intensity Transformations Using the Wasserstein Metric

Oskarsson, Magnus LU (2015) 19th Scandinavian Conference on Image Analysis (SCIA 2015) In Lecture Notes in Computer Science (Image Analysis, 19th Scandinavian Conference, SCIA 2015, Copenhagen, Denmark, June 15-17, 2015. Proceedings)) 9127. p.275-286
Abstract
In this paper we direct our attention to the problem of discretization effects in intensity transformations of images. We propose to use the Wasserstein metric (also known as the Earth mover distance) to bootstrap the transformation process. The Wasserstein metric gives a mapping between gray levels that we use to direct our image mapping. In order to spatially regularize the image mapping we apply anisotropic filtering and use this to steer our mapping. We describe a general framework for intensity transformation, and investigate the application of our method on a number of special problems, namely histogram equalization, color transfer and bit depth expansion. We have tested our algorithms on real images, and we show that we get... (More)
In this paper we direct our attention to the problem of discretization effects in intensity transformations of images. We propose to use the Wasserstein metric (also known as the Earth mover distance) to bootstrap the transformation process. The Wasserstein metric gives a mapping between gray levels that we use to direct our image mapping. In order to spatially regularize the image mapping we apply anisotropic filtering and use this to steer our mapping. We describe a general framework for intensity transformation, and investigate the application of our method on a number of special problems, namely histogram equalization, color transfer and bit depth expansion. We have tested our algorithms on real images, and we show that we get state-of-the-art results. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Image enhancement, Discretization, Wasserstein metric
in
Lecture Notes in Computer Science (Image Analysis, 19th Scandinavian Conference, SCIA 2015, Copenhagen, Denmark, June 15-17, 2015. Proceedings))
editor
Paulsen, Rasmus; Pedersen, Kim; and
volume
9127
pages
12 pages
publisher
Springer
conference name
19th Scandinavian Conference on Image Analysis (SCIA 2015)
external identifiers
  • scopus:84947938680
ISSN
1611-3349
0302-9743
ISBN
978-3-319-19665-7
978-3-319-19664-0
DOI
10.1007/978-3-319-19665-7_23
language
English
LU publication?
yes
id
71057566-a401-4d40-b9b6-b0ed14beeb17 (old id 8052142)
alternative location
http://link.springer.com/chapter/10.1007%2F978-3-319-19665-7_23
date added to LUP
2016-01-20 17:54:44
date last changed
2017-01-01 03:18:16
@inproceedings{71057566-a401-4d40-b9b6-b0ed14beeb17,
  abstract     = {In this paper we direct our attention to the problem of discretization effects in intensity transformations of images. We propose to use the Wasserstein metric (also known as the Earth mover distance) to bootstrap the transformation process. The Wasserstein metric gives a mapping between gray levels that we use to direct our image mapping. In order to spatially regularize the image mapping we apply anisotropic filtering and use this to steer our mapping. We describe a general framework for intensity transformation, and investigate the application of our method on a number of special problems, namely histogram equalization, color transfer and bit depth expansion. We have tested our algorithms on real images, and we show that we get state-of-the-art results.},
  author       = {Oskarsson, Magnus},
  booktitle    = {Lecture Notes in Computer Science (Image Analysis, 19th Scandinavian Conference, SCIA 2015, Copenhagen, Denmark, June 15-17, 2015. Proceedings))},
  editor       = {Paulsen, Rasmus and Pedersen, Kim},
  isbn         = {978-3-319-19665-7},
  issn         = {1611-3349},
  keyword      = {Image enhancement,Discretization,Wasserstein metric},
  language     = {eng},
  pages        = {275--286},
  publisher    = {Springer},
  title        = {Regularizing Image Intensity Transformations Using the Wasserstein Metric},
  url          = {http://dx.doi.org/10.1007/978-3-319-19665-7_23},
  volume       = {9127},
  year         = {2015},
}