Thin structure filtering framework with non-local means, Gaussian derivatives and spatially-variant mathematical morphology

Abstract : Thin structure filtering is an important preprocessing task for the analysis of 2D and 3D bio-medical images in various contexts. We propose a filtering framework that relies on three approaches that are distinct and infrequently used together: linear, non-linear and non-local. This strategy, based on recent progress both in algorithmic/computational and methodological points of view, provides results that benefit from the advantages of each approach, while reducing their respective weaknesses. Its relevance is demonstrated by validations on 2D and 3D images.
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.univ-reims.fr/hal-01719128
Contributor : Nicolas Passat <>
Submitted on : Wednesday, February 28, 2018 - 2:11:30 AM
Last modification on : Friday, October 4, 2019 - 1:30:34 AM
Long-term archiving on: Monday, May 28, 2018 - 1:59:01 PM

File

Nguyen_ICIP_2013.pdf
Files produced by the author(s)

Identifiers

Citation

Tuan-Anh Nguyen, Alice Dufour, Olena Tankyevych, Amir Nakib, Eric Petit, et al.. Thin structure filtering framework with non-local means, Gaussian derivatives and spatially-variant mathematical morphology. International Conference on Image Processing (ICIP), 2013, Melbourne, Australia. pp.1237-1241, ⟨10.1109/ICIP.2013.6738255⟩. ⟨hal-01719128⟩

Share

Metrics

Record views

235

Files downloads

227