Show simple item record

Detection of intentionally made changes in image content

dc.contributor.advisorReljin, Irini
dc.contributor.otherProkin, Milan
dc.contributor.otherSamčović, Andreja
dc.contributor.otherŠumarac-Pavlović, Dragana
dc.contributor.otherGavrovska, Ana
dc.creatorPavlović, Aleksandra S.
dc.date.accessioned2020-01-27T12:20:40Z
dc.date.available2020-01-27T12:20:40Z
dc.date.available2020-07-03T08:35:41Z
dc.date.issued2019-06-19
dc.identifier.urihttp://nardus.mpn.gov.rs/handle/123456789/11748
dc.identifier.urihttp://eteze.bg.ac.rs/application/showtheses?thesesId=7123
dc.identifier.urihttps://fedorabg.bg.ac.rs/fedora/get/o:20789/bdef:Content/download
dc.identifier.urihttp://vbs.rs/scripts/cobiss?command=DISPLAY&base=70036&RID=51821839
dc.description.abstractDigital images and video signals represent the most frequently transmitted contents. Namely, with the development of modern digital cameras and smartphones, the use of multimedia content increases every day. They are used in everyday life, for getting information and also as authenticated proofs or corroboratory evidence in different areas like: forensic studies, law enforcement, journalism and others...en
dc.description.abstractMultifraktalna analiza se pokazala kao dobar alat za analizu postojećih slika, kao i segmentaciju određenih regiona, izdvajanje ivica, uglova slike i slično. Kako kopirani i nalepljeni delovi imaju sličnu strukturu, može se primeniti multifraktalna analiza, koja u osnovi analizira samosličnost. Multifraktalni spektar daje globalni opis slike (ili, opštije, fenomena koji se ispituje). Vrednost Hölder-ovog eksponenta zavisi od položaja u strukturi i opisuje lokalnu regularnost signala. Naime, različiti objekti na slici imaju različite spektre, različite pozicije maksimuma, minimuma, prve nule itd, što se pokazalo kao interesantan skup različitih parametara pomoću kojih se mogu detektovati namerne promene na slikama...sr
dc.formatapplication/pdf
dc.languagesr
dc.publisherУниверзитет у Београду, Електротехнички факултетsr
dc.relationinfo:eu-repo/grantAgreement/MESTD/Technological Development (TD or TR)/32023/RS//
dc.relationinfo:eu-repo/grantAgreement/MESTD/MPN2006-2010/13018/RS//
dc.rightsopenAccessen
dc.sourceУниверзитет у Београдуsr
dc.subjectobrada slikesr
dc.subjectimage processingen
dc.subjectclusteringen
dc.subjectimage forensicsen
dc.subjectCMFD (copy-move forgery detection)en
dc.subjectmultifractal spectrumen
dc.subjectHölder exponenten
dc.subjectmetaheuristic methoden
dc.subjectsemi-metricen
dc.subjectklasterovanjesr
dc.subjectforenzika slikesr
dc.subjectCMFD (copy-move forgery detection)sr
dc.subjectmultifraktalni spektarsr
dc.subjectHölder-ov eksponentsr
dc.subjectmetaheuristikasr
dc.subjectsemi-metrikasr
dc.titleDetekcija namerno izazvanih promena u sadržaju slikesr
dc.title.alternativeDetection of intentionally made changes in image contenten
dc.typedoctoralThesis
dc.rights.licenseBY-NC-ND
dc.identifier.fulltexthttp://nardus.mpn.gov.rs/bitstream/id/5678/Disertacija.pdf
dc.identifier.fulltexthttp://nardus.mpn.gov.rs/bitstream/id/5679/IzvestajKomisije21623.pdf


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record