Difference between revisions of "Publications/xue.03.icip"
From LRDE
| (5 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
{{Publication |
{{Publication |
||
| − | | |
+ | | published = true |
| + | | date = 2003-04-10 |
||
| authors = Heru Xue, Thierry Géraud, Alexandre Duret-Lutz |
| authors = Heru Xue, Thierry Géraud, Alexandre Duret-Lutz |
||
| title = Multi-band segmentation using morphological clustering and fusion application to color image segmentation |
| title = Multi-band segmentation using morphological clustering and fusion application to color image segmentation |
||
| Line 7: | Line 8: | ||
| volume = 1 |
| volume = 1 |
||
| address = Barcelona, Spain |
| address = Barcelona, Spain |
||
| − | | |
+ | | lrdeprojects = Olena |
| − | | urllrde = 200309-Icip |
||
| abstract = In this paper we propose a novel approach for color image segmentation. Our approach is based on segmentation of subsets of bands using mathematical morphology followed by the fusion of the resulting segmentation channels. For color images the band subsets are chosen as RG, RB and GB pairs, whose 2D histograms are processed as projections of a 3D histogram. The segmentations in 2D color spaces are obtained using the watershed algorithm. These 2D segmentations are then combined to obtain a final result using a region split-and-merge process. The CIE L a b color space is used to measure the color distance. Our approach results in improved performance and can be generalized for multi-band segmentation of images such as multi-spectral satellite images information. |
| abstract = In this paper we propose a novel approach for color image segmentation. Our approach is based on segmentation of subsets of bands using mathematical morphology followed by the fusion of the resulting segmentation channels. For color images the band subsets are chosen as RG, RB and GB pairs, whose 2D histograms are processed as projections of a 3D histogram. The segmentations in 2D color spaces are obtained using the watershed algorithm. These 2D segmentations are then combined to obtain a final result using a region split-and-merge process. The CIE L a b color space is used to measure the color distance. Our approach results in improved performance and can be generalized for multi-band segmentation of images such as multi-spectral satellite images information. |
||
| lrdekeywords = Image |
| lrdekeywords = Image |
||
| + | | lrdenewsdate = 2003-04-10 |
||
| type = inproceedings |
| type = inproceedings |
||
| id = xue.03.icip |
| id = xue.03.icip |
||
| Line 25: | Line 26: | ||
address = <nowiki>{</nowiki>Barcelona, Spain<nowiki>}</nowiki>, |
address = <nowiki>{</nowiki>Barcelona, Spain<nowiki>}</nowiki>, |
||
month = sep, |
month = sep, |
||
| − | project = <nowiki>{</nowiki>Image<nowiki>}</nowiki>, |
||
abstract = <nowiki>{</nowiki>In this paper we propose a novel approach for color image |
abstract = <nowiki>{</nowiki>In this paper we propose a novel approach for color image |
||
segmentation. Our approach is based on segmentation of |
segmentation. Our approach is based on segmentation of |
||
Latest revision as of 18:58, 4 January 2018
- Authors
- Heru Xue, Thierry Géraud, Alexandre Duret-Lutz
- Where
- Proceedings of the IEEE International Conference on Image Processing (ICIP)
- Place
- Barcelona, Spain
- Type
- inproceedings
- Projects
- Olena
- Keywords
- Image
- Date
- 2003-04-10
Abstract
In this paper we propose a novel approach for color image segmentation. Our approach is based on segmentation of subsets of bands using mathematical morphology followed by the fusion of the resulting segmentation channels. For color images the band subsets are chosen as RG, RB and GB pairs, whose 2D histograms are processed as projections of a 3D histogram. The segmentations in 2D color spaces are obtained using the watershed algorithm. These 2D segmentations are then combined to obtain a final result using a region split-and-merge process. The CIE L a b color space is used to measure the color distance. Our approach results in improved performance and can be generalized for multi-band segmentation of images such as multi-spectral satellite images information.
Bibtex (lrde.bib)
@InProceedings{ xue.03.icip,
author = {Heru Xue and Thierry G\'eraud and Alexandre Duret-Lutz},
title = {Multi-band segmentation using morphological clustering and
fusion application to color image segmentation},
booktitle = {Proceedings of the IEEE International Conference on Image
Processing (ICIP)},
year = 2003,
pages = {353--356},
volume = 1,
address = {Barcelona, Spain},
month = sep,
abstract = {In this paper we propose a novel approach for color image
segmentation. Our approach is based on segmentation of
subsets of bands using mathematical morphology followed by
the fusion of the resulting segmentation channels. For
color images the band subsets are chosen as RG, RB and GB
pairs, whose 2D histograms are processed as projections of
a 3D histogram. The segmentations in 2D color spaces are
obtained using the watershed algorithm. These 2D
segmentations are then combined to obtain a final result
using a region split-and-merge process. The CIE L a b color
space is used to measure the color distance. Our approach
results in improved performance and can be generalized for
multi-band segmentation of images such as multi-spectral
satellite images information.}
}