General Purpose Segmentation for Microorganisms in Microscopy Images

S. N. Jensen, R. Irani, T. B. Moeslund, Christian Rankl

2014

Abstract

In this paper, we propose an approach for achieving generalized segmentation of microorganisms in microscopy images. It employs a pixel-wise classification strategy based on local features. Multilayer perceptrons are utilized for classification of the local features and is trained for each specific segmentation problem using supervised learning. This approach was tested on five different segmentation problems in bright field, differential interference contrast, fluorescence and laser confocal scanning microscopy. In all instance good results were achieved with the segmentation quality scoring a Dice coefficient of 0.831 or higher.

Paper Citation

in Harvard Style

Jensen S., Irani R., Moeslund T. and Rankl C. (2014). General Purpose Segmentation for Microorganisms in Microscopy Images . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-003-1, pages 690-695. DOI: 10.5220/0004827106900695

in Bibtex Style

@conference{visapp14,
author={S. N. Jensen and R. Irani and T. B. Moeslund and Christian Rankl},
title={General Purpose Segmentation for Microorganisms in Microscopy Images},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={690-695},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004827106900695},
isbn={978-989-758-003-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014)
TI - General Purpose Segmentation for Microorganisms in Microscopy Images
SN - 978-989-758-003-1
AU - Jensen S.
AU - Irani R.
AU - Moeslund T.
AU - Rankl C.
PY - 2014
SP - 690
EP - 695
DO - 10.5220/0004827106900695