A New Model for the Segmentation of Multiple, Overlapping, Near-Circular Objects

Csaba Molnar, Z. Kato, Ian H. Jermyn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Some of the most difficult image segmentation problems involve an unknown number of object instances that can touch or overlap in the image, e.g. microscopy imaging of cells in biology. In an important set of cases, the nature of the objects and the imaging process mean that when objects overlap, the resulting image is approximately given by the sum of intensities of individual objects; and, in addition, the objects of interest are 'blob-like' or near-circular. We propose a new model for the segmentation of the objects in such images. The posterior energy is the sum of a prior energy modelling shape and a likelihood energy modelling the image. The prior is a multi-layer nonlocal phase field energy that favours configurations consisting of a number of possibly overlapping or touching near-circular object instances. The likelihood energy models the additive nature of image intensity in regions corresponding to overlapping objects. We use variational methods to compute a MAP estimate of the object instances in an image. We test the resulting model on synthetic data and on fluorescence microscopy images of cell nuclei.

Original languageEnglish
Title of host publication2015 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781467367950
DOIs
Publication statusPublished - Jan 4 2016
EventInternational Conference on Digital Image Computing: Techniques and Applications, DICTA 2015 - Adelaide, Australia
Duration: Nov 23 2015Nov 25 2015

Other

OtherInternational Conference on Digital Image Computing: Techniques and Applications, DICTA 2015
CountryAustralia
CityAdelaide
Period11/23/1511/25/15

Fingerprint

Imaging techniques
Fluorescence microscopy
Image segmentation
Microscopic examination
Cells

ASJC Scopus subject areas

  • Computer Science Applications
  • Signal Processing

Cite this

Molnar, C., Kato, Z., & Jermyn, I. H. (2016). A New Model for the Segmentation of Multiple, Overlapping, Near-Circular Objects. In 2015 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2015 [7371219] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DICTA.2015.7371219

A New Model for the Segmentation of Multiple, Overlapping, Near-Circular Objects. / Molnar, Csaba; Kato, Z.; Jermyn, Ian H.

2015 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2015. Institute of Electrical and Electronics Engineers Inc., 2016. 7371219.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Molnar, C, Kato, Z & Jermyn, IH 2016, A New Model for the Segmentation of Multiple, Overlapping, Near-Circular Objects. in 2015 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2015., 7371219, Institute of Electrical and Electronics Engineers Inc., International Conference on Digital Image Computing: Techniques and Applications, DICTA 2015, Adelaide, Australia, 11/23/15. https://doi.org/10.1109/DICTA.2015.7371219
Molnar C, Kato Z, Jermyn IH. A New Model for the Segmentation of Multiple, Overlapping, Near-Circular Objects. In 2015 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2015. Institute of Electrical and Electronics Engineers Inc. 2016. 7371219 https://doi.org/10.1109/DICTA.2015.7371219
Molnar, Csaba ; Kato, Z. ; Jermyn, Ian H. / A New Model for the Segmentation of Multiple, Overlapping, Near-Circular Objects. 2015 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2015. Institute of Electrical and Electronics Engineers Inc., 2016.
@inproceedings{1479923811c647db83f89bba4f8cd9fa,
title = "A New Model for the Segmentation of Multiple, Overlapping, Near-Circular Objects",
abstract = "Some of the most difficult image segmentation problems involve an unknown number of object instances that can touch or overlap in the image, e.g. microscopy imaging of cells in biology. In an important set of cases, the nature of the objects and the imaging process mean that when objects overlap, the resulting image is approximately given by the sum of intensities of individual objects; and, in addition, the objects of interest are 'blob-like' or near-circular. We propose a new model for the segmentation of the objects in such images. The posterior energy is the sum of a prior energy modelling shape and a likelihood energy modelling the image. The prior is a multi-layer nonlocal phase field energy that favours configurations consisting of a number of possibly overlapping or touching near-circular object instances. The likelihood energy models the additive nature of image intensity in regions corresponding to overlapping objects. We use variational methods to compute a MAP estimate of the object instances in an image. We test the resulting model on synthetic data and on fluorescence microscopy images of cell nuclei.",
author = "Csaba Molnar and Z. Kato and Jermyn, {Ian H.}",
year = "2016",
month = "1",
day = "4",
doi = "10.1109/DICTA.2015.7371219",
language = "English",
isbn = "9781467367950",
booktitle = "2015 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A New Model for the Segmentation of Multiple, Overlapping, Near-Circular Objects

AU - Molnar, Csaba

AU - Kato, Z.

AU - Jermyn, Ian H.

PY - 2016/1/4

Y1 - 2016/1/4

N2 - Some of the most difficult image segmentation problems involve an unknown number of object instances that can touch or overlap in the image, e.g. microscopy imaging of cells in biology. In an important set of cases, the nature of the objects and the imaging process mean that when objects overlap, the resulting image is approximately given by the sum of intensities of individual objects; and, in addition, the objects of interest are 'blob-like' or near-circular. We propose a new model for the segmentation of the objects in such images. The posterior energy is the sum of a prior energy modelling shape and a likelihood energy modelling the image. The prior is a multi-layer nonlocal phase field energy that favours configurations consisting of a number of possibly overlapping or touching near-circular object instances. The likelihood energy models the additive nature of image intensity in regions corresponding to overlapping objects. We use variational methods to compute a MAP estimate of the object instances in an image. We test the resulting model on synthetic data and on fluorescence microscopy images of cell nuclei.

AB - Some of the most difficult image segmentation problems involve an unknown number of object instances that can touch or overlap in the image, e.g. microscopy imaging of cells in biology. In an important set of cases, the nature of the objects and the imaging process mean that when objects overlap, the resulting image is approximately given by the sum of intensities of individual objects; and, in addition, the objects of interest are 'blob-like' or near-circular. We propose a new model for the segmentation of the objects in such images. The posterior energy is the sum of a prior energy modelling shape and a likelihood energy modelling the image. The prior is a multi-layer nonlocal phase field energy that favours configurations consisting of a number of possibly overlapping or touching near-circular object instances. The likelihood energy models the additive nature of image intensity in regions corresponding to overlapping objects. We use variational methods to compute a MAP estimate of the object instances in an image. We test the resulting model on synthetic data and on fluorescence microscopy images of cell nuclei.

UR - http://www.scopus.com/inward/record.url?scp=84963692176&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84963692176&partnerID=8YFLogxK

U2 - 10.1109/DICTA.2015.7371219

DO - 10.1109/DICTA.2015.7371219

M3 - Conference contribution

SN - 9781467367950

BT - 2015 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -