A non-local Chan-Vese model for sparse, tubular object segmentation

Abstract : To deal with the issue of tubular object segmentation, we propose a new model involving a non-local fitting term, in the Chan-Vese framework. This model aims at detecting objects whose intensities are not necessarily piecewise constant, or even composed of multiple piecewise constant regions. Our problem formulation exploits object sparsity in the image domain and a local ordering relationship between foreground and background. A continuous optimization scheme can then be efficiently considered in this context. This approach is validated on both synthetic and real retinal images. The non-local data fitting term is shown to be superior to the classical piecewise-constant model, robust to noise and to low contrast.
Complete list of metadatas

Cited literature [31 references]  Display  Hide  Download

https://hal.univ-reims.fr/hal-01695066
Contributor : Nicolas Passat <>
Submitted on : Wednesday, February 7, 2018 - 2:12:24 PM
Last modification on : Wednesday, August 29, 2018 - 1:08:01 PM
Long-term archiving on : Thursday, May 3, 2018 - 7:17:13 PM

Identifiers

Citation

Anna Jezierska, Olivia Miraucourt, Hugues Talbot, Stéphanie Salmon, Nicolas Passat. A non-local Chan-Vese model for sparse, tubular object segmentation. International Conference on Image Processing (ICIP), 2014, Paris, France. pp.907-911, ⟨10.1109/ICIP.2014.7025182⟩. ⟨hal-01695066⟩

Share

Metrics

Record views

184

Files downloads

155