prikaz prve stranice dokumenta Detekcija istaknutih dijelova slike
  Download
PDF 129.07 KB
master's thesis
Detekcija istaknutih dijelova slike
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2014. urn:nbn:hr:200:091561
Tufeković, Jelena
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Visual Computing

Cite this document

Tufeković, J. (2014). Detekcija istaknutih dijelova slike (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:091561

Tufeković, Jelena. "Detekcija istaknutih dijelova slike." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2014. https://urn.nsk.hr/urn:nbn:hr:200:091561

Tufeković, Jelena. "Detekcija istaknutih dijelova slike." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2014. https://urn.nsk.hr/urn:nbn:hr:200:091561

Tufeković, J. (2014). 'Detekcija istaknutih dijelova slike', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 21 September 2024, https://urn.nsk.hr/urn:nbn:hr:200:091561

Tufeković J. Detekcija istaknutih dijelova slike [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2014 [cited 2024 September 21] Available at: https://urn.nsk.hr/urn:nbn:hr:200:091561

J. Tufeković, "Detekcija istaknutih dijelova slike", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2014. Available at: https://urn.nsk.hr/urn:nbn:hr:200:091561

Please login to the repository to save this object to your list.
Metadata
TitleDetekcija istaknutih dijelova slike
Title (english)Saliency detection
AuthorJelena Tufeković
MentorIrena Galić (mentor)
Committee memberIrena Galić (predsjednik povjerenstva)
Committee memberTomislav Keser (član povjerenstva)
Committee memberČaslav Livada (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Visual Computing)
Osijek
Defense date and country2014-10-17, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Process Computing
Abstract
Postoje mnoge metode za detekciju istaknutih dijelova slike, a neke od njih su: metoda detekcije pomoću frekvencije, metoda detekcije pomoću globalnog i lokalnog kontrasta te metoda detekcije pomoću konteksta. Metoda detekcije pomoću frekvencije koristi prostornu frekvenciju. Metoda detekcije pomoću globalnog kontrasta koristi histograme ili regije. Metoda detekcije na temelju lokalnog kontrasta koristi filtre. Metoda detekcije pomoću konteksta jedina izdvaja i kontekst slike te daje dobre rezultat ukoliko postoji barem jedan istaknuti objekt na slici koji se razlikuje od svoje pozadine
Abstract (english)
There are a lot of methods for detection of salient image regions, and some of them are: frequency based saliency detection, local and global contrast based saliency detection and context-aware saliency detection. Frequency based saliency detection uses spatial frequencies. Local contrast based saliency detection uses histograms or regions. Global contrast based saliency detection uses filters. Context-aware saliency detection is the only detection that includes context and provides good results if there is at least one salient object in the picture which differs from its background.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:091561
Study programmeTitle: Graduate University Study Programme in Computer Engineering
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 conditionsOpen access
Terms of useLicence In copyright icon
RepositoryFaculty of Electrical Engineering, Computer Science and Information Technology Osijek
Created on2016-07-01 10:00:31