by Milán Leskó, Zoltan Kato, Antal Nagy, Imre Gombos, Zsolt Török, László Vígh Jr, László Vígh
Abstract:
We propose a novel Markovian segmentation model which takes into account edge information. By construction, the model uses only pairwise interactions and its energy is submodular. Thus the exact energy minima is obtained via a max-flow/min-cut algorithm. The method has been quantitatively evaluated on synthetic images as well as on fluorescence microscopic images of live cells.
Reference:
Milán Leskó, Zoltan Kato, Antal Nagy, Imre Gombos, Zsolt Török, László Vígh Jr, László Vígh, Live Cell Segmentation in Fluorescence Microscopy via Graph Cut, In Proceedings of International Conference on Pattern Recognition, Istambul, Turkey, pp. 1485-1488, 2010, IEEE.
Bibtex Entry:
@string{icpr="Proceedings of International Conference on Pattern Recognition"}
@INPROCEEDINGS{Lesko-etal2010,
author = {Mil\'an Lesk\'o and Zoltan Kato and Antal Nagy and Imre Gombos and
Zsolt T\"or\"ok and L\'aszl\'o V\'igh Jr and L\'aszl\'o V\'igh},
title = {Live Cell Segmentation in Fluorescence Microscopy via Graph Cut},
booktitle = icpr,
year = {2010},
pages = {1485--1488},
address = {Istambul, Turkey},
month = aug,
organization = {IAPR},
publisher = {IEEE},
abstract = {We propose a novel Markovian segmentation model which takes into account
edge information. By construction, the model uses only pairwise interactions
and its energy is submodular. Thus the exact energy minima is obtained
via a max-flow/min-cut algorithm. The method has been quantitatively
evaluated on synthetic images as well as on fluorescence microscopic
images of live cells.},
pdf = {papers/icpr2010.pdf}
}