Publications Repository - Helmholtz-Zentrum Dresden-Rossendorf
1 PublicationSoftware for Bubble identification from images with machine learning methods
Heßenkemper, H.; Starke, S.; Atassi, Y.; Ziegenhein, T.; Lucas, D.
This package contains the software and the trained models described in the publication "Bubble identification from images with machine learning methods". Please refer to the README.md for installation instructions and to the Prediction_demo.ipynb for usage demonstration.
Update
The Prediction_demo.ipynb includes now an example how to prepare the predictions for the tracking algorithm of "Fate of bubble clusters rising in a quiescent liquid". The tracking code can be found here.
Update
Now only tensorflow models are used, so no MXNet installation required.
Keywords: Bubbly flows; Deep Learning; Computer Vision; CNN; Semantic segmentation
Related publications
- DOI: 10.1016/j.ijmultiphaseflow.2022.104169 references this (Id 34349) publication
-
Bubble identification from images with machine learning methods
ROBIS: 34350 has used this (Id 34349) publication of HZDR-primary research data
-
Software in the HZDR data repository RODARE
Publication date: 2022-08-05 Open access
DOI: 10.14278/rodare.1470
Versions: 10.14278/rodare.2566 | 10.14278/rodare.2329 | 10.14278/rodare.1830 | 10.14278/rodare.1471
License: CC-BY-4.0
Downloads
Permalink: https://www.hzdr.de/publications/Publ-34349