Institutional Repository of Vilnius University
Mikroplastiko dalelių segmentacija mikroskopiniuose vaizduose /
Abstract
dc:descriptionThis bachelor’s thesis tackles the rising need for quick, lowcost segmentation of microplastics in microscope images. Aster reviewing several deep learning segmentation approaches, a UNet based convolutional network was developed and trained on an FTMC image set. Data augmentation and hyperparameter tuning enabled the model to identify most particles accurately. Although background artefacts and limited training data still constrain performance, the study shows that UNet is suitable for microplastics particle search in microscopic images and highlights the value of larger, better annotated datasets for future work.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Pupelis, Lukas,
Rights
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:ELABAETD239032104&prefLang=en_US