Exploring Uncertainty in Image Segmentation Ensembles

dc.contributor.authorFröhler, Bernharden_US
dc.contributor.authorMöller, Torstenen_US
dc.contributor.authorWeissenböck, Johannesen_US
dc.contributor.authorHege, Hans-Christianen_US
dc.contributor.authorKastner, Johannen_US
dc.contributor.authorHeinzl, Christophen_US
dc.contributor.editorAnna Puig and Renata Raidouen_US
dc.date.accessioned2018-06-02T17:55:49Z
dc.date.available2018-06-02T17:55:49Z
dc.date.issued2018
dc.description.abstractFinding the most accurate image segmentation involves analyzing results from different algorithms or parameterizations. In this work, we identify different types of uncertainty in this analysis that are represented by the results of probabilistic algorithms, by the local variability in the segmentation, and by the variability across the segmentation ensemble. We propose visualization techniques for the analysis of such types of uncertainties in segmentation ensembles. For a global analysis we provide overview visualizations in the image domain as well as in the label space. Our probability probing and scatter plot based techniques facilitate a local analysis. We evaluate our techniques using a case study on industrial computed tomography data.en_US
dc.description.sectionheadersPosters
dc.description.seriesinformationEuroVis 2018 - Posters
dc.identifier.doi10.2312/eurp.20181123
dc.identifier.isbn978-3-03868-065-9
dc.identifier.pages33-35
dc.identifier.urihttps://doi.org/10.2312/eurp.20181123
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/eurp20181123
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectImage segmentation
dc.subjectUncertainty quantification
dc.titleExploring Uncertainty in Image Segmentation Ensemblesen_US
Files
Original bundle
Now showing 1 - 3 of 3
Loading...
Thumbnail Image
Name:
033-035.pdf
Size:
313.78 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
1025-file2.pdf
Size:
371.64 KB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
1025-file3.mp4
Size:
3.36 MB
Format:
Unknown data format