Difference between revisions of "Publications/movn.22.pr"
From LRDE
(Created page with "{{Publication | published = true | date = 2022-12-03 | authors = Minh Ôn Vũ Ngoc, Edwin Carlinet, Jonathan Fabrizio, Thierry Géraud | title = The Dahu Graph-Cut for Interac...") |
|||
| (2 intermediate revisions by the same user not shown) | |||
| Line 5: | Line 5: | ||
| title = The Dahu Graph-Cut for Interactive Segmentation on 2D/3D Images |
| title = The Dahu Graph-Cut for Interactive Segmentation on 2D/3D Images |
||
| journal = Pattern Recognition |
| journal = Pattern Recognition |
||
| + | | volume = 136 |
||
| number = 109207 |
| number = 109207 |
||
| abstract = Interactive image segmentation is an important application in computer vision for selecting objects of interest in images. Several interactive segmentation methods are based on distance transform algorithms. However, the most known distance transform, geodesic distance, is sensitive to noise in the image and to seed placement. Recently, the Dahu pseudo-distance, a continuous version of the minimum barrier distance (MBD), is proved to be more powerful than the geodesic distance in noisy and blurred images. This paper presents a method for combining the Dahu pseudo-distance with edge information in a graph-cut optimization framework and leveraging each's complementary strengths. Our method works efficiently on both 2D/3D images and videos. Results show that our method achieves better performance than other distance-based and graph-cut methods, thereby reducing the user's efforts. |
| abstract = Interactive image segmentation is an important application in computer vision for selecting objects of interest in images. Several interactive segmentation methods are based on distance transform algorithms. However, the most known distance transform, geodesic distance, is sensitive to noise in the image and to seed placement. Recently, the Dahu pseudo-distance, a continuous version of the minimum barrier distance (MBD), is proved to be more powerful than the geodesic distance in noisy and blurred images. This paper presents a method for combining the Dahu pseudo-distance with edge information in a graph-cut optimization framework and leveraging each's complementary strengths. Our method works efficiently on both 2D/3D images and videos. Results show that our method achieves better performance than other distance-based and graph-cut methods, thereby reducing the user's efforts. |
||
| lrdeprojects = Olena |
| lrdeprojects = Olena |
||
| lrdekeywords = Image |
| lrdekeywords = Image |
||
| + | | lrdepaper = https://www.lrde.epita.fr/dload/papers/movn.22.pr.pdf |
||
| lrdenewsdate = 2022-12-03 |
| lrdenewsdate = 2022-12-03 |
||
| type = article |
| type = article |
||
| Line 20: | Line 22: | ||
<nowiki>{</nowiki>2D/3D<nowiki>}</nowiki> Images<nowiki>}</nowiki>, |
<nowiki>{</nowiki>2D/3D<nowiki>}</nowiki> Images<nowiki>}</nowiki>, |
||
journal = <nowiki>{</nowiki>Pattern Recognition<nowiki>}</nowiki>, |
journal = <nowiki>{</nowiki>Pattern Recognition<nowiki>}</nowiki>, |
||
| − | year = <nowiki>{</nowiki> |
+ | year = <nowiki>{</nowiki>2023<nowiki>}</nowiki>, |
| + | volume = <nowiki>{</nowiki>136<nowiki>}</nowiki>, |
||
number = <nowiki>{</nowiki>109207<nowiki>}</nowiki>, |
number = <nowiki>{</nowiki>109207<nowiki>}</nowiki>, |
||
| − | month = |
+ | month = apr, |
abstract = <nowiki>{</nowiki>Interactive image segmentation is an important application |
abstract = <nowiki>{</nowiki>Interactive image segmentation is an important application |
||
in computer vision for selecting objects of interest in |
in computer vision for selecting objects of interest in |
||
Latest revision as of 15:45, 8 December 2022
- Authors
- Minh Ôn Vũ Ngoc, Edwin Carlinet, Jonathan Fabrizio, Thierry Géraud
- Journal
- Pattern Recognition
- Type
- article
- Projects
- Olena
- Keywords
- Image
- Date
- 2022-12-03
Abstract
Interactive image segmentation is an important application in computer vision for selecting objects of interest in images. Several interactive segmentation methods are based on distance transform algorithms. However, the most known distance transform, geodesic distance, is sensitive to noise in the image and to seed placement. Recently, the Dahu pseudo-distance, a continuous version of the minimum barrier distance (MBD), is proved to be more powerful than the geodesic distance in noisy and blurred images. This paper presents a method for combining the Dahu pseudo-distance with edge information in a graph-cut optimization framework and leveraging each's complementary strengths. Our method works efficiently on both 2D/3D images and videos. Results show that our method achieves better performance than other distance-based and graph-cut methods, thereby reducing the user's efforts.
Documents
Bibtex (lrde.bib)
@Article{ movn.22.pr,
author = {Minh \^On V\~{u} Ng\d{o}c and Edwin Carlinet and Jonathan
Fabrizio and Thierry G\'eraud},
title = {The {D}ahu Graph-Cut for Interactive Segmentation on
{2D/3D} Images},
journal = {Pattern Recognition},
year = {2023},
volume = {136},
number = {109207},
month = apr,
abstract = {Interactive image segmentation is an important application
in computer vision for selecting objects of interest in
images. Several interactive segmentation methods are based
on distance transform algorithms. However, the most known
distance transform, geodesic distance, is sensitive to
noise in the image and to seed placement. Recently, the
Dahu pseudo-distance, a continuous version of the minimum
barrier distance (MBD), is proved to be more powerful than
the geodesic distance in noisy and blurred images. This
paper presents a method for combining the Dahu
pseudo-distance with edge information in a graph-cut
optimization framework and leveraging each's complementary
strengths. Our method works efficiently on both 2D/3D
images and videos. Results show that our method achieves
better performance than other distance-based and graph-cut
methods, thereby reducing the user's efforts.},
doi = {10.1016/j.patcog.2022.109207}
}