Difference between revisions of "Publications/geraud.03.ibpria"
From LRDE
Line 1: | Line 1: | ||
{{Publication |
{{Publication |
||
− | | date = 2003- |
+ | | date = 2003-03-10 |
| authors = Thierry Géraud |
| authors = Thierry Géraud |
||
| title = Segmentation of curvilinear objects using a watershed-based curve adjacency graph |
| title = Segmentation of curvilinear objects using a watershed-based curve adjacency graph |
||
Line 14: | Line 14: | ||
| abstract = This paper presents a general framework to segment curvilinear objects in 2D images. A pre-processing step relies on mathematical morphology to obtain a connected line which encloses curvilinear objects. Then, a graph is constructed from this line and a Markovian Random Field is defined to perform objects segmentation. Applications of our framework are numerous: they go from simple surve segmentation to complex road network extraction in satellite images. |
| abstract = This paper presents a general framework to segment curvilinear objects in 2D images. A pre-processing step relies on mathematical morphology to obtain a connected line which encloses curvilinear objects. Then, a graph is constructed from this line and a Markovian Random Field is defined to perform objects segmentation. Applications of our framework are numerous: they go from simple surve segmentation to complex road network extraction in satellite images. |
||
| lrdekeywords = Image |
| lrdekeywords = Image |
||
+ | | lrdenewsdate = 2003-03-10 |
||
| type = inproceedings |
| type = inproceedings |
||
| id = geraud.03.ibpria |
| id = geraud.03.ibpria |
Revision as of 16:45, 5 November 2013
- Authors
- Thierry Géraud
- Where
- Proceedings of the 1st Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA)
- Place
- Mallorca, Spain
- Type
- inproceedings
- Publisher
- Springer-Verlag
- Keywords
- Image
- Date
- 2003-03-10
Abstract
This paper presents a general framework to segment curvilinear objects in 2D images. A pre-processing step relies on mathematical morphology to obtain a connected line which encloses curvilinear objects. Then, a graph is constructed from this line and a Markovian Random Field is defined to perform objects segmentation. Applications of our framework are numerous: they go from simple surve segmentation to complex road network extraction in satellite images.
Bibtex (lrde.bib)
@InProceedings{ geraud.03.ibpria, author = {Thierry G\'eraud}, title = {Segmentation of curvilinear objects using a watershed-based curve adjacency graph}, booktitle = {Proceedings of the 1st Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA)}, pages = {279--286}, year = 2003, editor = {Springer-Verlag}, volume = 2652, series = {Lecture Notes in Computer Science Series}, address = {Mallorca, Spain}, month = jun, publisher = {Springer-Verlag}, project = {Image}, abstract = {This paper presents a general framework to segment curvilinear objects in 2D images. A pre-processing step relies on mathematical morphology to obtain a connected line which encloses curvilinear objects. Then, a graph is constructed from this line and a Markovian Random Field is defined to perform objects segmentation. Applications of our framework are numerous: they go from simple surve segmentation to complex road network extraction in satellite images.} }