prikaz prve stranice dokumenta Duboke neuronske mreže za poboljšanje slika u boji
No public access
master's thesis
Duboke neuronske mreže za poboljšanje slika u boji
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. urn:nbn:hr:168:672738
Ivančan, Jakov
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Ivančan, J. (2018). Duboke neuronske mreže za poboljšanje slika u boji (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:672738

Ivančan, Jakov. "Duboke neuronske mreže za poboljšanje slika u boji." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:672738

Ivančan, Jakov. "Duboke neuronske mreže za poboljšanje slika u boji." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:672738

Ivančan, J. (2018). 'Duboke neuronske mreže za poboljšanje slika u boji', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 27 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:672738

Ivančan J. Duboke neuronske mreže za poboljšanje slika u boji [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2018 [cited 2024 December 27] Available at: https://urn.nsk.hr/urn:nbn:hr:168:672738

J. Ivančan, "Duboke neuronske mreže za poboljšanje slika u boji", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:168:672738

Metadata
TitleDuboke neuronske mreže za poboljšanje slika u boji
Title (english)Deep neural networks for color image enhancement
AuthorJakov Ivančan
MentorSven Lončarić (mentor)
Committee memberSven Lončarić (predsjednik povjerenstva)
Committee memberMarko Subašić (član povjerenstva)
Committee memberTomislav Petković (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2018-07-03, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Računalna postojanost boje je sposobnost uklanjanja efekta boje izvora na svjetlosti sa slika kako bi slika izgledala kao da je slikana pod kanonskim, bijelim svjetlom. U zadnje vrijeme, konvolucijske neuronske mreže ostvaruju state-of-the-art rezultate u zadacima obrade slike, uključujući i problem računalne postojanosti boje. U sklopu ovog rada prestavljena je potpuno konvolucijska neuronska mreža za rješavanje problema postojanosti boje na računalu. Također, opisani su skupovi za učenje korišteni za treniranje mreže te rezultati koje je mrea potigla.
Abstract (english)
Color constancy is the ability to account for the color of the light source in images so that images look like they were shot under a canonical light source (usually white light). Lately, convolutional neural networks brought state-of-the-art performance in various image processing tasks, including computational color constancy. In this paper, fully convolutional neural network is introduced to solve this task along with datasets used to train the network as well as results which the network accomplished.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:672738
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 on2019-03-13 20:58:28