prikaz prve stranice dokumenta Računalno raspoznavanje vrste glagoljskog pisma
No public access
master's thesis
Računalno raspoznavanje vrste glagoljskog pisma
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. urn:nbn:hr:168:934281
Ursa, Ivana
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Ursa, I. (2022). Računalno raspoznavanje vrste glagoljskog pisma (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:934281

Ursa, Ivana. "Računalno raspoznavanje vrste glagoljskog pisma." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:934281

Ursa, Ivana. "Računalno raspoznavanje vrste glagoljskog pisma." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:934281

Ursa, I. (2022). 'Računalno raspoznavanje vrste glagoljskog pisma', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 04 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:934281

Ursa I. Računalno raspoznavanje vrste glagoljskog pisma [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2022 [cited 2024 November 04] Available at: https://urn.nsk.hr/urn:nbn:hr:168:934281

I. Ursa, "Računalno raspoznavanje vrste glagoljskog pisma", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:168:934281

Metadata
TitleRačunalno raspoznavanje vrste glagoljskog pisma
Title (english)Computer Recognition of Glagolitic Script Type
AuthorIvana Ursa
MentorMislav Grgić (mentor)
Committee memberMislav Grgić (predsjednik povjerenstva)
Committee memberSonja Grgić (član povjerenstva)
Committee memberTomislav Kos (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2022-07-06, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Računalni vid je grana umjetne inteligencije koja se bavi raspoznavanjem te izvlačenjem informacija iz slika i videozapisa. Jedan od mnogih problema koje rješava računalni vid jest raspoznavanje teksta ili simbola na slikama, nakon čega može slijediti transkripcija i prevođenje. Glagoljica je najstarije slavensko pismo koje se koristilo od 9. stoljeća pa sve do 19. stoljeća. Kroz svoju povijest poprimala je različite oblike te zbog toga razlikuju se tri vrste glagoljice: trokutasta, obla i uglata. Te vrste glagoljice mogu se računalno raspoznavati korištenjem konvolucijskih neuronskih mreža. Kako je teško postići dovoljno velik skup slika za treniranje zbog ograničenog broja dostupnih dokumenata na glagoljici, korištenjem metode prijenosa znanja mogu se postići vrlo dobri rezultati i uz umjeren broj primjera za treniranje neuronske mreže.
Abstract (english)
Computer vision is a branch of artificial intelligence that deals with recognizing and extracting information from images and videos. One of the many problems that computer vision solves is the recognition of text or symbols in images, which can be followed by transcription and translation. Glagolitic script is the oldest Slavic alphabet used from the 9th century until the 19th century. Throughout its history, it has taken different forms and therefore three types of Glagolitic script are distinguished: triangular, round, and angular. These types of Glagolitic script can be digitally recognized using convolutional neural networks. As it is difficult to achieve a large enough image dataset for training due to the limited amount of available Glagolitic documents, using transfer learning can achieve very good results and with a moderate size of training dataset for the neural network.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:934281
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-01-13 16:25:34