Deep Learning in palynology
dc.contributor.author | Viertel, Philipp | |
dc.contributor.author | König, Matthias | |
dc.contributor.editor | Meyer-Aurich, Andreas | |
dc.contributor.editor | Gandorfer, Markus | |
dc.contributor.editor | Hoffmann, Christa | |
dc.contributor.editor | Weltzien, Cornelia | |
dc.contributor.editor | Bellingrath-Kimura, Sonoko | |
dc.contributor.editor | Floto, Helga | |
dc.date.accessioned | 2021-03-02T14:37:32Z | |
dc.date.available | 2021-03-02T14:37:32Z | |
dc.date.issued | 2021 | |
dc.description.abstract | In this work, we will show a use case for visual pollen classification from honey samples. We discuss the current state of the art in pollen analysis, highlight the importance of data quantity and quality, and elaborate on how to transfer promising Deep Learning methods to the analysis of honey samples. A first experiment with a public data set is shown as well as samples from our work-in-progress data set. Our recommendations and methods show which steps are necessary in order to successfully deploy an automated pollen analysis solution for honey products. | en |
dc.identifier.isbn | 978-3-88579-703-6 | |
dc.identifier.pissn | 1617-5468 | |
dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/35697 | |
dc.language.iso | en | |
dc.publisher | Gesellschaft für Informatik e.V. | |
dc.relation.ispartof | 41. GIL-Jahrestagung, Informations- und Kommunikationstechnologie in kritischen Zeiten | |
dc.relation.ispartofseries | Lecture Notes in Informatics | |
dc.subject | Deep Learning | |
dc.subject | Machine Learning | |
dc.subject | Palynology | |
dc.subject | Pollen analysis | |
dc.subject | Automation | |
dc.title | Deep Learning in palynology | en |
dc.type | Text/Conference Paper | |
gi.citation.endPage | 336 | |
gi.citation.publisherPlace | Bonn | |
gi.citation.startPage | 331 | |
gi.conference.date | 08.-09. März 2021 | |
gi.conference.location | Potsdam, Online | |
gi.conference.sessiontitle | GIL-Jahrestagung - Fokus: Informations- und Kommunikationstechnologien in kritischen Zeiten |
Dateien
Originalbündel
1 - 1 von 1
Lade...
- Name:
- GIL2021_Viertel_331-336.pdf
- Größe:
- 535.81 KB
- Format:
- Adobe Portable Document Format