Advanced

Image segmentation with context

Eriksson, Anders P LU ; Olsson, Carl LU and Kahl, Fredrik LU (2007) 15th Scandinavian Image Analysis Conference In Proceedings 15th Scandinavian Image Analysis Conference 4522. p.283-292
Abstract
We present a technique for simultaneous segmentation and classification of image partitions using combinatorial optimization techniques. By combining existing image segmentation approaches with simple learning techniques we show how prior knowledge can be incorporated into the visual grouping process through the formulation of a quadratic binary optimization problem. We further show how such to efficiently solve such problems through relaxation techniques and trust, region methods. This has resulted in an method that partitions images into a number of disjoint regions based on previously learned example segmentations. Preliminary experimental results are also presented in support of our suggested approach.
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
visual grouping process, learning technique, combinatorial optimization technique, image segmentation, image classification, relaxation technique, quadratic binary optimization problem
in
Proceedings 15th Scandinavian Image Analysis Conference
volume
4522
pages
283 - 292
publisher
Springer
conference name
15th Scandinavian Image Analysis Conference
external identifiers
  • WOS:000247364000029
  • Scopus:38049037993
DOI
10.1007/978-3-540-73040-8_29
language
English
LU publication?
yes
id
c7e2ba1f-5614-42a5-9e49-c5b5ec9b1f0e (old id 643424)
date added to LUP
2007-12-04 14:36:55
date last changed
2017-01-01 07:56:35
@inproceedings{c7e2ba1f-5614-42a5-9e49-c5b5ec9b1f0e,
  abstract     = {We present a technique for simultaneous segmentation and classification of image partitions using combinatorial optimization techniques. By combining existing image segmentation approaches with simple learning techniques we show how prior knowledge can be incorporated into the visual grouping process through the formulation of a quadratic binary optimization problem. We further show how such to efficiently solve such problems through relaxation techniques and trust, region methods. This has resulted in an method that partitions images into a number of disjoint regions based on previously learned example segmentations. Preliminary experimental results are also presented in support of our suggested approach.},
  author       = {Eriksson, Anders P and Olsson, Carl and Kahl, Fredrik},
  booktitle    = {Proceedings 15th Scandinavian Image Analysis Conference},
  keyword      = {visual grouping process,learning technique,combinatorial optimization technique,image segmentation,image classification,relaxation technique,quadratic binary optimization problem},
  language     = {eng},
  pages        = {283--292},
  publisher    = {Springer},
  title        = {Image segmentation with context},
  url          = {http://dx.doi.org/10.1007/978-3-540-73040-8_29},
  volume       = {4522},
  year         = {2007},
}