Institutional Repository of Vilnius University
Vaizdų dalinės informacijos panaudojimas jų atpažinime /
Abstract
dc:descriptionImage recognition is one of the most important and rapidly evolving computer science fields. It helps to automate various object recognition tasks with minimum human intervention. It is not an uncommon practice to apply image processing techniques before implementing machine learning model. The aim of this work was to analyse partial image data application in image recognition. Partial image information was extracted by implementing an application that generates a random path of pixels. This method was used in three different experiments - digit recognition, histopathological cancer recognition and diabetic retinopathy recognition from optic disks. In each experiment a machine learning model was implemented. Results had shown that partial image data generated in such way can be used for image recognition tasks with simple and complex initial data.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2020
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Norvaišaitė, Goda,
- Contributors dc:contributor
-
- Grinis, Irus
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:ELABAETD81804883&prefLang=en_US