Back to search
Institutional Repository of Vilnius University
Žiedadulkių rūšių atpažinimas kompiuterine rega /
Abstract
dc:descriptionPollen type recognition is a difficult task, which requires operator. Convolutional neural networks are the best option as an alternative for human eyes.In this study eighteen different pretrained and easily available architecture models, which were trained based on transfer learning for pollen recognition.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2019
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Bialoglovis, Arnoldas,
- Contributors dc:contributor
-
- Daunys, Gintautas
Subjects
dc:subject × 1Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD38038014&prefLang=en_US