prikaz prve stranice dokumenta Duboko učenje za bojenje crno-bijelih slika
No public access
undergraduate thesis
Duboko učenje za bojenje crno-bijelih slika
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. urn:nbn:hr:168:351214
Balić, Stella
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Balić, S. (2023). Duboko učenje za bojenje crno-bijelih slika (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:351214

Balić, Stella. "Duboko učenje za bojenje crno-bijelih slika." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:351214

Balić, Stella. "Duboko učenje za bojenje crno-bijelih slika." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:351214

Balić, S. (2023). 'Duboko učenje za bojenje crno-bijelih slika', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 29 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:351214

Balić S. Duboko učenje za bojenje crno-bijelih slika [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 November 29] Available at: https://urn.nsk.hr/urn:nbn:hr:168:351214

S. Balić, "Duboko učenje za bojenje crno-bijelih slika", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:351214

Metadata
TitleDuboko učenje za bojenje crno-bijelih slika
Title (english)Deep Learning for Colorizing of Grayscale Images
AuthorStella Balić
MentorSven Lončarić (mentor)
Committee memberSven Lončarić (predsjednik povjerenstva)
Committee memberDonik Vršnak (član povjerenstva)
Committee memberFran Huzjan (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2023-07-04, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Duboko učenje sve se više upotrebljava u području računalnog vida kako bi se postigli rezultati koji nisu rješivi klasičnim matematičkim modelima. Svoju primjenu pronašlo je i u bojanju crno-bijelih fotografija, što nam je jako praktično za oživljavanje starih monokromatskih slika. U okviru rada ukratko je opisana je teorijska podloga umjetnih neuronskih mreža i dubokog učenja, a naglasak je na generativnim suparničkim mrežama (GANs). Jedan GAN model korišten je za praktično ostvarenje rješenja ovog problema te je predstavljena njegova arhitektura, eksperimentalni rezultati, poboljšanja i dodatne ideje za korištenje.
Abstract (english)
Deep learning is increasingly being used in the field of computer vision to achieve results that are not solvable by classical mathematical models. It has also found application in colorizing black and white images, which is highly practical for reviving old monochromatic images. Within this work, a brief overview of the theoretical foundation of artificial neural networks and deep learning is provided, with emphasis on generative adversarial networks (GANs). One GAN model was used to practically implement a solution to this problem, and its architecture, experimental results, improvements, and additional ideas are presented.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:351214
Study programmeTitle: Computing
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-10-11 08:20:52