prikaz prve stranice dokumenta Automatsko bojanje crno-bijelih fotografija putem dubokog učenja
No public access
master's thesis
Automatsko bojanje crno-bijelih fotografija putem dubokog učenja
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. urn:nbn:hr:168:726619
Ladić, Helena
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Ladić, H. (2024). Automatsko bojanje crno-bijelih fotografija putem dubokog učenja (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:726619

Ladić, Helena. "Automatsko bojanje crno-bijelih fotografija putem dubokog učenja." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:726619

Ladić, Helena. "Automatsko bojanje crno-bijelih fotografija putem dubokog učenja." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:726619

Ladić, H. (2024). 'Automatsko bojanje crno-bijelih fotografija putem dubokog učenja', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 28 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:726619

Ladić H. Automatsko bojanje crno-bijelih fotografija putem dubokog učenja [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2024 [cited 2024 December 28] Available at: https://urn.nsk.hr/urn:nbn:hr:168:726619

H. Ladić, "Automatsko bojanje crno-bijelih fotografija putem dubokog učenja", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:168:726619

Metadata
TitleAutomatsko bojanje crno-bijelih fotografija putem dubokog učenja
Title (english)Automatic Colorization of Black and White Photos Using Deep Learning
AuthorHelena Ladić
MentorVladimir Čeperić (mentor)
Committee memberVladimir Čeperić (predsjednik povjerenstva)
Committee memberZoran Kalafatić (član povjerenstva)
Committee memberTomislav Marković (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2024-07-17, Croatia
Abstract
Rad se bavi problematikom automatskog bojanja slika putem dubokog učenja. Detaljnije je opisano nekoliko različitih arhitektura koje rješavaju problem bojanja. Izabrano je nekoliko dubokih modela čiji je postupak rada opisan kroz poglavlja. Analiza rezultata bojanja provedena je na testnom skupu podataka Gustava Klimta. Spomenute su i izračunate često korištene metrike za evaluaciju kvalitete generiranih slika. Navedeni su neki od nedostataka i mogućnosti daljnjeg poboljšanja i nadogradnje.
Abstract (english)
The paper addresses the issue of automatic image colorization using deep learning. Several different architectures that solve the colorization problem are described in detail. Several deep models were selected, and their working procedure is explained throughout the chapters. The colorization results were analyzed on a Gustav Klimt test dataset. Frequently used metrics for evaluating the quality of generated images are mentioned and calculated. Some of the drawbacks and possibilities for further improvement are also listed.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:726619
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 on2024-10-12 21:18:01