Segmentation des IRM cérébrales par une variante bootstrapée du HMRF-EM : étude préliminaire sur fantômes

M'Hiri, Slim; Mabrouk, Sabra; Ghorbel, Faouzi

doi:10.1016/j.irbm.2011.12.005

Cited by 3 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Interested in accelerating statistical segmentation based on the family of Expectation-Maximization algorithms, the authors in [6] propose to resample the image by the Bootstrap with a reduced number of pixels to minimize on the one hand the computational time and on the other hand the correlation between the observations. For the same purpose, we were interested in [8] to the contextual classification of brain Magnetic Resonance Images (MRI) via the EM algorithm, combined with the Markovian assumption for both observation and label fields, the algorithm is so called (Hidden Markov Random Field Estimation maximization) HMRF-EM. The principle is to randomly draw from the uniform distribution of the 2D image coordinates and then keep the pixels gray levels.…”

Section: Introductionmentioning

confidence: 99%

A new representative criterion for image resampling based on bootstrap and plug in algorithm

2014

View full text Add to dashboard Cite

In this paper we intend to introduce a new representativeness criterion of the Bootstrap sample for images segmentation. Using the plug-in method in order to estimate probability density functions (pdf), we present a robust and stable criterion based on L 2 distance between the estimated probability density from the bootstrap sample and the empirical probability density of the image. This criterion is tested on satellite images.

show abstract

Section: Introductionmentioning

confidence: 99%