2010
DOI: 10.1007/978-3-642-12110-4_29
|View full text |Cite
|
Sign up to set email alerts
|

Regionalized Random Germs by a Classification for Probabilistic Watershed Application: Angiogenesis Imaging Segmentation

Abstract: Summary. New methods are presented to generate random germs regionalized by a previous classification in order to use probabilistic watershed on hyperspectral images. These germs are much more efficient than the standard uniform random germs.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
6
0

Year Published

2010
2010
2015
2015

Publication Types

Select...
4
1

Relationship

2
3

Authors

Journals

citations
Cited by 5 publications
(6 citation statements)
references
References 5 publications
0
6
0
Order By: Relevance
“…So-called "stochastic watersheds" [1] are especially suited to the segmentation of granular microstructures of the type considered here, as they are aimed at unsupervised segmentation [26]. This consists in using a predefined number n of random markers to build a probability density function (PDF) of contours.…”
Section: Stochastic Watershedsmentioning
confidence: 99%
“…So-called "stochastic watersheds" [1] are especially suited to the segmentation of granular microstructures of the type considered here, as they are aimed at unsupervised segmentation [26]. This consists in using a predefined number n of random markers to build a probability density function (PDF) of contours.…”
Section: Stochastic Watershedsmentioning
confidence: 99%
“…In 2014 Malmberg and Luengo Hendriks [191] presented an efficient algorithm for computing the exact stochastic watershed without any randomness. Stochastic watershed has been applied to several medical image segmentation problems, such as study of angiogenesis [192], segmentation of granular materials in 3D micro-tomography [193], and detection of the optic disc in fundus images [194].…”
Section: B Watershed Methodsmentioning
confidence: 99%
“…To do this, it is possible to use point germs or random ball germs whose location is conditioned by the classification. An exhaustive study of the germs is presented in (Noyel, 2008;Noyel et al, 2010b). Below, we present random ball germs regionalized by a classification where each connected class may be hit one time, mrk κ−b i (x).…”
Section: Conditioning Of the Germs Of The Pdf By A Previous Classificmentioning
confidence: 99%
“…The algorithm in table 4 sketches the process. Note that if N is the number of random germs to be generated, the effective number of implanted germs is lower than N. if C k , such as m ∈ C k , is not marked then 7: In Noyel et al (2010b), the pdf built with these germs seemed to give better results than others. Therefore, the results shown use these germs.…”
Section: Conditioning Of the Germs Of The Pdf By A Previous Classificmentioning
confidence: 99%