Difference between revisions of "Publications/movn.20.cviu"

From LRDE

 
Line 13: Line 13:
 
| type = article
 
| type = article
 
| id = movn.20.cviu
 
| id = movn.20.cviu
  +
| identifier = doi:10.1016/j.cviu.2020.102993
 
| bibtex =
 
| bibtex =
 
@Article<nowiki>{</nowiki> movn.20.cviu,
 
@Article<nowiki>{</nowiki> movn.20.cviu,
Line 24: Line 25:
 
month = aug,
 
month = aug,
 
volume = <nowiki>{</nowiki>197--198<nowiki>}</nowiki>,
 
volume = <nowiki>{</nowiki>197--198<nowiki>}</nowiki>,
  +
doi = <nowiki>{</nowiki>10.1016/j.cviu.2020.102993<nowiki>}</nowiki>,
 
abstract = <nowiki>{</nowiki>Distance transforms and the saliency maps they induce are
 
abstract = <nowiki>{</nowiki>Distance transforms and the saliency maps they induce are
 
widely used in image processing, computer vision, and
 
widely used in image processing, computer vision, and

Latest revision as of 11:47, 24 November 2020

Abstract

Distance transforms and the saliency maps they induce are widely used in image processing, computer vision, and pattern recognition. One of the most commonly used distance transform is the geodesic one. Unfortunately, this distance does not always achieve satisfying results on noisy or blurred images. Recently, a new (pseudo-)distance, called the minimum barrier distance (MBD), more robust to pixel variations, has been introduced. Some years after, Géraud et al. have proposed a good and fast-to compute approximation of this distance: the Dahu pseudo-distance. Since this distance was initially developped for grayscale images, we propose here an extension of this transform to multivariate images; we call it vectorial Dahu pseudo-distance. An efficient way to compute it is provided in this paper. Besides, we provide benchmarks demonstrating how much the vectorial Dahu pseudo-distance is more robust and competitive compared to other MB-based distances, which shows how much this distance is promising for salient object detection, shortest path finding, and object segmentation.

Documents

Bibtex (lrde.bib)

@Article{	  movn.20.cviu,
  author	= {Minh {\^On V\~{u} Ng\d{o}c} and Nicolas Boutry and
		  Jonathan Fabrizio and Thierry G\'eraud},
  title		= {A New Minimum Barrier Distance for Multivariate Images
		  with Applications to Salient Object Detection, Shortest
		  Path Finding, and Segmentation},
  journal	= {Computer Vision and Image Understanding},
  year		= {2020},
  month		= aug,
  volume	= {197--198},
  doi		= {10.1016/j.cviu.2020.102993},
  abstract	= {Distance transforms and the saliency maps they induce are
		  widely used in image processing, computer vision, and
		  pattern recognition. One of the most commonly used distance
		  transform is the geodesic one. Unfortunately, this distance
		  does not always achieve satisfying results on noisy or
		  blurred images. Recently, a new (pseudo-)distance, called
		  the minimum barrier distance (MBD), more robust to pixel
		  variations, has been introduced. Some years after, G\'eraud
		  et al. have proposed a good and fast-to compute
		  approximation of this distance: the Dahu pseudo-distance.
		  Since this distance was initially developped for grayscale
		  images, we propose here an extension of this transform to
		  multivariate images; we call it vectorial Dahu
		  pseudo-distance. An efficient way to compute it is provided
		  in this paper. Besides, we provide benchmarks demonstrating
		  how much the vectorial Dahu pseudo-distance is more robust
		  and competitive compared to other MB-based distances, which
		  shows how much this distance is promising for salient
		  object detection, shortest path finding, and object
		  segmentation.}
}