prikaz prve stranice dokumenta Strojno učenje u modnoj industriji
No public access
undergraduate thesis
Strojno učenje u modnoj industriji
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. urn:nbn:hr:168:464314
Rosandić, Nika
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Rosandić, N. (2018). Strojno učenje u modnoj industriji (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:464314

Rosandić, Nika. "Strojno učenje u modnoj industriji." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:464314

Rosandić, Nika. "Strojno učenje u modnoj industriji." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:464314

Rosandić, N. (2018). 'Strojno učenje u modnoj industriji', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 03 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:464314

Rosandić N. Strojno učenje u modnoj industriji [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2018 [cited 2024 November 03] Available at: https://urn.nsk.hr/urn:nbn:hr:168:464314

N. Rosandić, "Strojno učenje u modnoj industriji", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:168:464314

Metadata
TitleStrojno učenje u modnoj industriji
Title (english)Machine Learning for Fashion Industry
AuthorNika Rosandić
MentorVladimir Čeperić (mentor)
Committee memberVladimir Čeperić (predsjednik povjerenstva)
Committee memberIvan Krešo (član povjerenstva)
Committee memberMartin Soldić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2018-07-13, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom se radu, teorijski i praktično, razmatra primjena strojnog učenja u modnoj industriji. U teorijskom dijelu predstavljaju se problemi modne industrije koji se mogu riješiti strojnim učenjem. Uvodi se strojno učenje i njegove grane te duboko učenje i neuronske mreže. Detaljnije se obrađuju generativne kontradiktorne mreže. U praktičnom se dijelu analizira model pretvorbe skice cipele u stvarnu sliku cipele. Objašnjen je algoritam konvolucijskih generativnih kontradiktornih mreža kao trenutno najbolje rješenje takvog problema umjetne inteligencije, njihovo treniranje i testiranje. Analizirana mreža trenirana je na jednom skupu slika cipela, te potom testirana na dva različita skupa.
Abstract (english)
This paper analyzes the use of machine learning in fashion industry, both theoretically and practically. It introduces problems in fashion industry today which can be solved with machine learning algorithms. Machine learning and its branches, as well as deep learning and neural networks are theoretically presented. Generative adversarial networks are specifically analyzed. In the practical part of this paper, an image-to-image translation algorithm with purpose of translating shoe sketches into images of real shoes is analyzed in depth. Convolutional neural networks are described as, currently, the optimal solution to solving this type of artificial intelligence problem. Analyzed network is trained using a specific large dataset of shoe images, and afterwards tested on two different shoe datasets.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:464314
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 on2019-03-14 00:31:00