Characterizing the Structure Tensor Using Gamma Distributions
(2017) 2016 23rd International Conference on Pattern Recognition (ICPR 2016) p.763-768- Abstract
- The structure tensor is a powerful tool describing the local intensity structure of an image or image sequence. In this paper we give a model for the noise distribution of the components of the tensor. In order to do so we have also investigated some properties of the gamma distribution. We show that, given an input image corrupted with Gaussian noise, the noise in the structure tensor can be modeled well by gamma distributions. We apply our model to automatic contrast enhancement of images taken under poor illumination. We show how our noise model can be used for automatic parameter selection in the filtering process, giving powerful results without the need for cumbersome parameter tuning.
- Abstract (Swedish)
- The structure tensor is a powerful tool describing the local intensity structure of an image or image sequence. In this paper we give a model for the noise distribution of the components of the tensor. In order to do so we have also investigated some properties of the gamma distribution. We show that, given an input image corrupted with Gaussian noise, the noise in the structure tensor can be modeled well by gamma distributions. We apply our model to automatic contrast enhancement of images taken under poor illumination. We show how our noise model can be used for automatic parameter selection in the filtering process, giving powerful results without the need for cumbersome parameter tuning.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/3a7667c8-6add-41f6-a31f-f4601968c163
- author
- Oskarsson, Magnus LU
- organization
- publishing date
- 2017-04-24
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Enhancement, restoration and filtering, Signal, image and video processing, Computational photography
- host publication
- Pattern Recognition (ICPR), 2016 23rd International Conference on
- pages
- 6 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 2016 23rd International Conference on Pattern Recognition (ICPR 2016)
- conference location
- Cancún, Mexico
- conference dates
- 2016-12-04 - 2016-12-08
- external identifiers
-
- scopus:85019092215
- ISBN
- 978-1-5090-4847-2
- DOI
- 10.1109/ICPR.2016.7899727
- language
- English
- LU publication?
- yes
- id
- 3a7667c8-6add-41f6-a31f-f4601968c163
- date added to LUP
- 2016-12-12 15:47:09
- date last changed
- 2022-01-30 08:27:24
@inproceedings{3a7667c8-6add-41f6-a31f-f4601968c163, abstract = {{The structure tensor is a powerful tool describing the local intensity structure of an image or image sequence. In this paper we give a model for the noise distribution of the components of the tensor. In order to do so we have also investigated some properties of the gamma distribution. We show that, given an input image corrupted with Gaussian noise, the noise in the structure tensor can be modeled well by gamma distributions. We apply our model to automatic contrast enhancement of images taken under poor illumination. We show how our noise model can be used for automatic parameter selection in the filtering process, giving powerful results without the need for cumbersome parameter tuning.}}, author = {{Oskarsson, Magnus}}, booktitle = {{Pattern Recognition (ICPR), 2016 23rd International Conference on}}, isbn = {{978-1-5090-4847-2}}, keywords = {{Enhancement; restoration and filtering; Signal, image and video processing; Computational photography}}, language = {{eng}}, month = {{04}}, pages = {{763--768}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{Characterizing the Structure Tensor Using Gamma Distributions}}, url = {{https://lup.lub.lu.se/search/files/18131668/structure_stats_final.pdf}}, doi = {{10.1109/ICPR.2016.7899727}}, year = {{2017}}, }