Bayesian Non Local Means-Based Speckle filtering - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2008

Bayesian Non Local Means-Based Speckle filtering


In ultrasound (US) imaging, denoising is intended to improve quantitative image analysis techniques. In this paper, a new version of the Non Local (NL) Means filter adapted for US images is proposed. Originally developed for Gaussian noise removal, a Bayesian framework is used to adapt the NL means filter for speckle noise. Experiments were carried out on synthetic data sets with different speckle simulations. Results show that our NL means-based speckle filter outperforms the classical implementation of the NL means filter, as well as two other speckle adapted denoising methods (SRAD and SBF filters).
Fichier principal
Vignette du fichier
Coupe08c.pdf (383.32 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00283477 , version 1 (30-05-2008)


  • HAL Id : inria-00283477 , version 1


Pierrick Coupé, Pierre Hellier, Charles Kervrann, Christian Barillot. Bayesian Non Local Means-Based Speckle filtering. IEEE International Symposium on Biomedical Imaging: From Nano to Macro, May 2008, Paris, France. ⟨inria-00283477⟩
251 View
1081 Download


Gmail Facebook X LinkedIn More