prikaz prve stranice dokumenta Detekcija lažnih slika i video zapisa putem dubokog učenja
No public access
undergraduate thesis
Detekcija lažnih slika i video zapisa putem dubokog učenja
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. urn:nbn:hr:168:840616
Pešut, Filip
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Pešut, F. (2023). Detekcija lažnih slika i video zapisa putem dubokog učenja (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:840616

Pešut, Filip. "Detekcija lažnih slika i video zapisa putem dubokog učenja." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:840616

Pešut, Filip. "Detekcija lažnih slika i video zapisa putem dubokog učenja." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:840616

Pešut, F. (2023). 'Detekcija lažnih slika i video zapisa putem dubokog učenja', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 26 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:840616

Pešut F. Detekcija lažnih slika i video zapisa putem dubokog učenja [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 November 26] Available at: https://urn.nsk.hr/urn:nbn:hr:168:840616

F. Pešut, "Detekcija lažnih slika i video zapisa putem dubokog učenja", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:840616

Metadata
TitleDetekcija lažnih slika i video zapisa putem dubokog učenja
Title (english)Deep Learning Based Deepfakes Detection
AuthorFilip Pešut
MentorVladimir Čeperić (mentor)
Committee memberVladimir Čeperić (predsjednik povjerenstva)
Committee memberVlatko Galić (član povjerenstva)
Committee memberAlma Traživuk (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2023-06-30, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Fokus ovog rada je bio opisati problem i postojeće načine upotrebe dubokog učenja, specifično, dubokih konvolucijskih modela, za detekciju lažnih slika i video zapisa (eng. deepfakes). Izabrati prikladan tip dubokih konvolucijskih modela za implementaciju za navedenu primjenu i obrazložiti odabir. U radu je predložen model baziran na EfficientNet oblitelji konvolucijskih modela za detekciju lažnih video sadržaja i slika. Predloženi model nastoji povećati efikasnost i točnost postojećih modela te otvoriti nove puteve u borbi protiv lažnih video zapisa.
Abstract (english)
The focus of this paper was to describe the problem and existing ways of using deep learning, specifically, deep convolutional models, for the detection of fake images and videos (deepfakes). Choose the appropriate type of deep convolutional models to implement for the given application and justify the choice. The paper proposes a model based on the EfficientNet family of convolutional models for the detection of fake video content and images. The proposed model aims to increase the efficiency and accuracy of existing models and open new ways in the fight against fake videos.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:840616
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 on2023-07-13 10:27:55