Reference : Two methods of random seed generation to avoid over-segmentation with stochastic wate...
Scientific journals : Article
Engineering, computing & technology : Materials science & engineering
http://hdl.handle.net/2268/29664
Two methods of random seed generation to avoid over-segmentation with stochastic watershed: application to nuclear fuel micrographs
English
Cativa Tolosa, Sebastian [ > > ]
Blacher, Silvia mailto [Université de Liège - ULg > Département des sciences cliniques > Labo de biologie des tumeurs et du développement >]
Denis, Alicia [ > > ]
Marajovsky, Adolfo [ > > ]
Pirard, Jean-Paul mailto [Université de Liège - ULg > Département de chimie appliquée > Génie chimique - Génie catalytique >]
Gommes, Cédric mailto [Université de Liège - ULg > Département de chimie appliquée > Génie chimique - Génie catalytique >]
2009
Journal of Microscopy
Blackwell Publishing
236
79-86
Yes (verified by ORBi)
International
0022-2720
1365-2818
Oxford
United Kingdom
[en] Image Analysis ; Watershed ; Stochastic algorithms
[en] A stochastic version of the watershed algorithm is obtained by choosing randomly in the image the seeds from which the watershed regions are grown. The output of the procedure is a probability density function (PDF) corresponding to the probability that each pixel belongs to a boundary. In the present paper, two stochastic seed-generation processes are explored to avoid over-segmentation. The first is a non-uniform Poisson process, the density of which is optimized on the basis of opening granulometry. The second process positions the seeds randomly within disks centered on the maxima of a distance map. The two methods are applied to characterize the grain structure of nuclear fuel pellets. Estimators are proposed for the total edge length and grain number per unit area, LA and NA, which take advantage of the probabilistic nature of the PDF and do not require segmentation.
Fonds de la Recherche Scientifique (Communauté française de Belgique) - F.R.S.-FNRS ; Agence internationale à l'énergie atomique
Researchers ; Professionals ; Students
http://hdl.handle.net/2268/29664

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Restricted access
2009 J. Microscopy Stochastic Watershed.pdfPublisher postprint6.59 MBRequest copy

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.