Abstract
dc:descriptionIn this paper popular binarization and object detection methods are examined and the effect of binarization method on object detection methods is evaluated. Forms used for cell growth are used for various experiments and they must not be damaged. Their detection can be automated with various object detection methods. The effectiveness of these methods can be enhanced by binarizing the images, although that does not guarantee better results. The experiment concluded that for decent quality images Otsu binarization method was the only one which produced better results. For low quality pictures, usage of binarization methods produced worse results.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2020
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Maceika, Kazimieras Povilas,
- Contributors dc:contributor
-
- Plankis, Tomas
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:ELABAETD81706508&prefLang=en_US