Institutional Repository of Vilnius University
Biomedicininių ligų identifikavimas panaudojant fraktalų analizę /
Abstract
dc:descriptionIn this thesis, a set of images consisting of various benign and cancerous (melanoma) skin lesions were analyzed. During the initial data processing, a data noise removal tool was developed, which was based on morphological operations. In addition, a skin lesion was identified and its contour and texture were extracted. Fractal properties such as fractal dimension and lacunarity are further used to analyze skin lesions. Different calculations were performed to get these properties: Minkowski fractal dimension, Gliding-Box, DBC and PLS algorithms. A comparison of different classification models was made with the obtained fractal properties. Finally, the automated melanoma identification model was developed based on the functionalities developed during this work.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2021
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Šitkauskas, Lukas,
- Contributors dc:contributor
-
- Ričkus, Liutauras
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:ELABAETD107116757&prefLang=en_US