[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.
Disciplines :
Materials science & engineering
Author, co-author :
Cativa Tolosa, Sebastian
Blacher, Silvia ; Université de Liège - ULiège > Département des sciences cliniques > Labo de biologie des tumeurs et du développement
Denis, Alicia
Marajovsky, Adolfo
Pirard, Jean-Paul ; Université de Liège - ULiège > Département de chimie appliquée > Génie chimique - Génie catalytique
Gommes, Cédric ; Université de Liège - ULiège > Département de chimie appliquée > Génie chimique - Génie catalytique
Language :
English
Title :
Two methods of random seed generation to avoid over-segmentation with stochastic watershed: application to nuclear fuel micrographs
Publication date :
2009
Journal title :
Journal of Microscopy
ISSN :
0022-2720
eISSN :
1365-2818
Publisher :
Blackwell Publishing, Oxford, United Kingdom
Volume :
236
Pages :
79-86
Peer reviewed :
Peer Reviewed verified by ORBi
Funders :
F.R.S.-FNRS - Fonds de la Recherche Scientifique [BE] IAEA - International Atomic Energy Agency [AT]
Ángulo, J., Jeulin, D., (2007) Stochastic Watershed Segmentation, pp. 265-276. , Proc. Int. Symp. Mathematical Morphology ISMM'2007. Rio de Janeiro, Instituto Nacional de Pesquisas Espaciais (INPE), São Josè dos Campos
Bailly, H., Ménessier, D., Prunier, C., (1999) The Nuclear Fuel of Pressurized Water Reactors and Fast Reactors, Design and Behavior, , Lavoisier. Paris
Beucher, S., (1994) Watershed, Hierarchical Segmentation and Waterfall Algorithm, pp. 69-76. , Proc. Int. Symp. Mathematical Morphology ISMM'1994. Fontainebleau, Kluwer, Dordrecht
Gommes, C., Blacher, S., Masenelli-Varlot, K., Al, E., Image analysis characterization of multi-walled carbon nanotubes (2003) Carbon, 41, pp. 2561-2572
Horgan, G.W., Mathematical morphology for analysing soil structure from Images (1998) Eur. J. Soil Sci., 49, pp. 161-173
Najman, L., Schmitt, M., Geodesic saliency of watershed contours and hierachical segmentation. (1996) IEEE Trans. Pattern Anal. Mach. Intell., 18, pp. 1163-1173
Noyel, G., Angulo, J., Jeulin, D., Random germs and stochastic watershed for unsupervised multispectral image segmentation (2007) Lecture Notes in Computer Science, 4694, pp. 17-24. , ed. by. B. Apolloni. R.J. Howlett& C.J. Lakhmi. pp. Springer. Berlin
Ohser, J., Mücklich, F., (2000) Statistical Analysis of Microstructures in Materials Science., , Wiley. Chichester
Otsu, N., A threshold selection method from gray-level histograms. (1979) IEEE Trans. Syst. Man Cybernet., 9, pp. 62-66