Retour

RootPainter: Deep Learning Segmentation of Biological Images with Corrective Annotation

Type de document
journalArticle
Langue source
Anglais
Titre français
Titre anglais
RootPainter: Deep Learning Segmentation of Biological Images with Corrective Annotation
Auteur(s)
  • SMITH Abraham George
  • HAN Eusun
  • PETERSEN Jens
  • OLSEN Niels Alvin Faircloth
  • GIESE Christian
  • ATHMANN Miriam
  • DRESBØLL Dorte Bodin
  • THORUP-KRISTENSEN Kristian
Editeur(s)
Autre(s)
Id
T7AU3AV4
Version
2773
Url zotero
https://www.zotero.org/groups/2567444/items/T7AU3AV4
Date ajout
7 janvier 2021 14:14
Date modification
7 janvier 2021 14:14
Résumé anglais
We present RootPainter, a GUI-based software tool for the rapid training of deep neural networks for use in biological image analysis. RootPainter facilitates both fully-automatic and semi-automatic image segmentation. We investigate the effectiveness of RootPainter using three plant image datasets, evaluating its potential for root length extraction from chicory roots in soil, biopore counting and root nodule counting from scanned roots. We also use RootPainter to compare dense annotations to corrective ones which are added during the training based on the weaknesses of the current model.
Note
None
CRAW tags
  • AB - Transversal
  • FREDO biologie et travail du sol
  • FREDO technologie et innovation
  • GEO Allemagne
  • GEO Danemark
  • biopore
  • data base
WEB tags
Titre de la publication
bioRxiv
Pages
2020.04.16.044461
Date caractères
2020-05-12
Date publication
12 mai 2020
Doi
10.1101/2020.04.16.044461 Le DOI est une URL unique de référencement d'une publication. Il est donc plus fiable et permanent qu'une URL classique
Url publication
https://www.biorxiv.org/content/10.1101/2020.04.16.044461v2