Image Segmentation with Joint Regularization and Histogram Separation
(2015) In Master’s Theses in Mathematical Sciences FMA820 20151Mathematics (Faculty of Engineering)
- Abstract
- In this thesis optimization methods for image segmentation are studied. The common theme of all the methods is that we have a histogram model for appearance terms that we optimize jointly with smoothness. Recently it has been shown that if one assumes a histogram model for appearance, it is possible to optimize an approximation of the energy using only one graph cut, by ignoring the non-submodular volumetric penalty term. We show how to include the volumetric term using the Fast trust region framework. Fast trust region is a recently proposed method that is able to handle a large class of non-submodular energies by solving a sequence of graph cut problems. A comparison of these methods shows that Fast trust region typically obtains a lower... (More)
- In this thesis optimization methods for image segmentation are studied. The common theme of all the methods is that we have a histogram model for appearance terms that we optimize jointly with smoothness. Recently it has been shown that if one assumes a histogram model for appearance, it is possible to optimize an approximation of the energy using only one graph cut, by ignoring the non-submodular volumetric penalty term. We show how to include the volumetric term using the Fast trust region framework. Fast trust region is a recently proposed method that is able to handle a large class of non-submodular energies by solving a sequence of graph cut problems. A comparison of these methods shows that Fast trust region typically obtains a lower energy value and higher segmentation quality, at the cost of requiring multiple graph cuts.
Furthermore, we extend the simple histogram term to the multi-class setting and show that it is possible to optimize it with alpha-expansions. This is applied to the problems of stereo depth estimation and geometric model fitting. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/5403412
- author
- Nilsson, David LU
- supervisor
-
- Carl Olsson LU
- organization
- course
- FMA820 20151
- year
- 2015
- type
- H2 - Master's Degree (Two Years)
- subject
- publication/series
- Master’s Theses in Mathematical Sciences
- report number
- LUTFMA-3272-2015
- ISSN
- 1404-6342
- other publication id
- 2015:E12
- language
- English
- id
- 5403412
- date added to LUP
- 2015-06-18 12:11:26
- date last changed
- 2015-06-18 12:11:26
@misc{5403412, abstract = {{In this thesis optimization methods for image segmentation are studied. The common theme of all the methods is that we have a histogram model for appearance terms that we optimize jointly with smoothness. Recently it has been shown that if one assumes a histogram model for appearance, it is possible to optimize an approximation of the energy using only one graph cut, by ignoring the non-submodular volumetric penalty term. We show how to include the volumetric term using the Fast trust region framework. Fast trust region is a recently proposed method that is able to handle a large class of non-submodular energies by solving a sequence of graph cut problems. A comparison of these methods shows that Fast trust region typically obtains a lower energy value and higher segmentation quality, at the cost of requiring multiple graph cuts. Furthermore, we extend the simple histogram term to the multi-class setting and show that it is possible to optimize it with alpha-expansions. This is applied to the problems of stereo depth estimation and geometric model fitting.}}, author = {{Nilsson, David}}, issn = {{1404-6342}}, language = {{eng}}, note = {{Student Paper}}, series = {{Master’s Theses in Mathematical Sciences}}, title = {{Image Segmentation with Joint Regularization and Histogram Separation}}, year = {{2015}}, }