Back to search
Institutional Repository of Vilnius University
Simbolių atpažinimas įvairiomis sąlygomis taikant dėmesio sutelkimo mechanizmus /
Abstract
dc:descriptionThis paper focuses on one of the branches of computer vision - Optical character recognition (OCR) in the wild. A practical study is then carried out to find out which of the technologies is superior for this task - the long short-term memory model (LSTM) or the Attention mechanism. From the results of the study, it was concluded that the long short-term memory model performs better if a model architecture with convolutional neural networks is used.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Virbalis, Aidas,
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:ELABAETD192846492&prefLang=en_US