Automatic Fusion of Segmentation and Tracking Labels

D 2019

Automatic Fusion of Segmentation and Tracking Labels

AKBAŞ, Cem Emre, Vladimír ULMAN, Martin MAŠKA, Florian JUG, Michal KOZUBEK et. al.

Basic information

Original name

Automatic Fusion of Segmentation and Tracking Labels

Authors

AKBAŞ, Cem Emre (792 Turkey, guarantor, belonging to the institution), Vladimír ULMAN (203 Czech Republic, belonging to the institution), Martin MAŠKA (203 Czech Republic, belonging to the institution), Florian JUG (276 Germany) and Michal KOZUBEK (203 Czech Republic, belonging to the institution)

Edition

LNCS 11134. Switzerland, Computer Vision – ECCV 2018 Workshops, p. 446-454, 9 pp. 2019

Publisher

Springer Nature

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Switzerland

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

printed version "print"

References:

URL

Impact factor

Impact factor: 0.402 in 2005

RIV identification code

RIV/00216224:14330/19:00107241

Organization unit

Faculty of Informatics

ISBN

978-3-030-11023-9

ISSN

DOI

http://dx.doi.org/10.1007/978-3-030-11024-6_34

UT WoS

000594200000034

Keywords in English

Label fusion; Image annotation; Segmentation labels; Tracking labels

Abstract

V originále

Labeled training images of high quality are required for developing well-working analysis pipelines. This is, of course, also true for biological image data, where such labels are usually hard to get. We distinguish human labels (gold corpora) and labels generated by computer algorithms (silver corpora). A naturally arising problem is to merge multiple corpora into larger bodies of labeled training datasets. While fusion of labels in static images is already an established field, dealing with labels in time-lapse image data remains to be explored. Obtaining a gold corpus for segmentation is usually very time-consuming and hence expensive. For this reason, gold corpora for object tracking often use object detection markers instead of dense segmentations. If dense segmentations of tracked objects are desired later on, an automatic merge of the detection-based gold corpus with (silver) corpora of the individual time points for segmentation will be necessary. Here we present such an automatic merging system and demonstrate its utility on corpora from the Cell Tracking Challenge. We additionally release all label fusion algorithms as freely available and open plugins for Fiji (https://github.com/xulman/CTC-FijiPlugins).

Links

GBP302/12/G157, research and development project

Name: Dynamika a organizace chromosomů během buněčného cyklu a při diferenciaci v normě a patologii

Investor: Czech Science Foundation

MUNI/A/0854/2017, interní kód MU

Name: Rozsáhlé výpočetní systémy: modely, aplikace a verifikace VII.

Investor: Masaryk University, Category A

Citovat

AKBAŞ, Cem Emre, Vladimír ULMAN, Martin MAŠKA, Florian JUG and Michal KOZUBEK. Automatic Fusion of Segmentation and Tracking Labels. In Laura Leal-Taixé, Stefan Roth. Computer Vision – ECCV 2018 Workshops. LNCS 11134. Switzerland: Springer Nature, 2019, p. 446-454. ISBN 978-3-030-11023-9. Available from: https://dx.doi.org/10.1007/978-3-030-11024-6_34.

@inproceedings{1490221,
   author = {Akbaş, Cem Emre and Ulman, Vladimír and Maška, Martin and Jug, Florian and Kozubek, Michal},
   address = {Switzerland},
   booktitle = {Computer Vision – ECCV 2018 Workshops},
   doi = {http://dx.doi.org/10.1007/978-3-030-11024-6_34},
   edition = {LNCS 11134},
   editor = {Laura Leal-Taixé, Stefan Roth},
   keywords = {Label fusion; Image annotation; Segmentation labels; Tracking labels},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Switzerland},
   isbn = {978-3-030-11023-9},
   pages = {446-454},
   publisher = {Springer Nature},
   title = {Automatic Fusion of Segmentation and Tracking Labels},
   url = {https://link.springer.com/chapter/10.1007/978-3-030-11024-6_34},
   year = {2019}
}

TY  - JOUR
ID  - 1490221
AU  - Akbaş, Cem Emre - Ulman, Vladimír - Maška, Martin - Jug, Florian - Kozubek, Michal
PY  - 2019
TI  - Automatic Fusion of Segmentation and Tracking Labels
PB  - Springer Nature
CY  - Switzerland
SN  - 9783030110239
KW  - Label fusion
KW  - Image annotation
KW  - Segmentation labels
KW  - Tracking labels
UR  - https://link.springer.com/chapter/10.1007/978-3-030-11024-6_34
L2  - https://link.springer.com/chapter/10.1007/978-3-030-11024-6_34
N2  - Labeled training images of high quality are required for developing well-working analysis pipelines. This is, of course, also true for biological image data, where such labels are usually hard to get. We distinguish human labels (gold corpora) and labels generated by computer algorithms (silver corpora). A naturally arising problem is to merge multiple corpora into larger bodies of labeled training datasets. While fusion of labels in static images is already an established field, dealing with labels in time-lapse image data remains to be explored. Obtaining a gold corpus for segmentation is usually very time-consuming and hence expensive. For this reason, gold corpora for object tracking often use object detection markers instead of dense segmentations. If dense segmentations of tracked objects are desired later on, an automatic merge of the detection-based gold corpus with (silver) corpora of the individual time points for segmentation will be necessary. Here we present such an automatic merging system and demonstrate its utility on corpora from the Cell Tracking Challenge. We additionally release all label fusion algorithms as freely available and open plugins for Fiji (https://github.com/xulman/CTC-FijiPlugins).
ER  -

AKBA$\backslash$C S, Cem Emre, Vladimír ULMAN, Martin MAŠKA, Florian JUG and Michal KOZUBEK. Automatic Fusion of Segmentation and Tracking Labels. In Laura Leal-Taixé, Stefan Roth. \textit{Computer Vision – ECCV 2018 Workshops}. LNCS 11134. Switzerland: Springer Nature, 2019, p.~446-454. ISBN~978-3-030-11023-9. Available from: https://dx.doi.org/10.1007/978-3-030-11024-6\_{}34.

Detailed Information on Publication Record