Cells Detection Using Segmentation Competition

Emmanuelle Poulain 1 Sylvain Prigent 1 Emmanuel Soubies 1 Xavier Descombes 1
1 MORPHEME - Morphologie et Images
CRISAM - Inria Sophia Antipolis - Méditerranée , IBV - Institut de Biologie Valrose : U1091, Laboratoire I3S - SIS - Signal, Images et Systèmes
Abstract : In this paper we address the problem of cells detection from mi-croscopy images. We construct a dictionary of candidate shapes obtained from previous segmentation maps and define an energy function to select the best candidates. The energy minimization is performed by an iterative graph cut algorithm. The proposed approach optimally combines the segmentation maps obtained with different methods and/or parameters. We show on synthetic and real data that this process allows to drastically improve the performance of each individual segmentation.
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal.inria.fr/hal-01113167
Contributor : Emmanuel Soubies <>
Submitted on : Wednesday, February 4, 2015 - 3:33:43 PM
Last modification on : Monday, November 5, 2018 - 3:52:02 PM
Long-term archiving on : Wednesday, May 27, 2015 - 5:08:02 PM

File

Poulain_ISBI15.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Emmanuelle Poulain, Sylvain Prigent, Emmanuel Soubies, Xavier Descombes. Cells Detection Using Segmentation Competition. ISBI - International Symposium on Biomedical Imaging, Apr 2015, Brooklyn, United States. ⟨10.1109/ISBI.2015.7164090⟩. ⟨hal-01113167⟩

Share

Metrics

Record views

548

Files downloads

339