prikaz prve stranice dokumenta Kolorizacija crno-bijelih slika utemeljena na metodama strojnog učenja
No public access
master's thesis
Kolorizacija crno-bijelih slika utemeljena na metodama strojnog učenja
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. urn:nbn:hr:168:099160
Šimić, Marin
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Šimić, M. (2022). Kolorizacija crno-bijelih slika utemeljena na metodama strojnog učenja (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:099160

Šimić, Marin. "Kolorizacija crno-bijelih slika utemeljena na metodama strojnog učenja." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:099160

Šimić, Marin. "Kolorizacija crno-bijelih slika utemeljena na metodama strojnog učenja." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:099160

Šimić, M. (2022). 'Kolorizacija crno-bijelih slika utemeljena na metodama strojnog učenja', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 04 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:099160

Šimić M. Kolorizacija crno-bijelih slika utemeljena na metodama strojnog učenja [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:168:099160

M. Šimić, "Kolorizacija crno-bijelih slika utemeljena na metodama strojnog učenja", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:168:099160

Metadata
TitleKolorizacija crno-bijelih slika utemeljena na metodama strojnog učenja
Title (english)Grayscale Image Colorization Based on Machine Learning Methods
AuthorMarin Šimić
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
Rad se bavi problematikom kolorizacije crno-bijelih slika. Ovisno o razini ljudske interakcije metode kolorizacije dijele se na one koje zahtijevaju ljudsku interakciju (scribble- based i example-based metode) i na one automatske, temeljene na dubokom učenju. Naveden je i razvoj dubokog učenja, od najjednostavnije neuronske mreže, do kompleksnih sustava na kojima se temelji računalni vid. Opisane su i komponente konvolucijske neuronske mreže. Za praktični dio rada izrađena je i naučena konvolucijska neuronska mreža za bojanje crno-bijelih slika voća. Rezultati su evaluirani subjektivnom procjenom neovisnih promatrača i objektivnim metodama za procjenu kvalitete obojanih slika.
Abstract (english)
This paper focuses on problems involving back and white image colorization. Depending on the level of human interaction, colorization methods are divided into two categories: methods that require human interaction (scribble-based and example-based methods) and automatic methods that are based on deep learning and do not require human interaction while colouring. History of deep learning is also mentioned, from the first neural network all the way to the more complex solutions used for computer vision. Convolutional neural network and its components are described in detail. For the practical part of the paper, a convolutional neural network is constructed and trained for the purpose of colouring black and white images of fruits. Colorization results are evaluated using subjective opinions of two subjects, as well as objective methods used for evaluating colorized images.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:099160
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 16:16:52