prikaz prve stranice dokumenta Detekcija vrhova slike
  Download
PDF 1.51 MB
undergraduate thesis
Detekcija vrhova slike
2018. urn:nbn:hr:200:679463
Pejković, Ana
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

Pejković, A. (2018). Detekcija vrhova slike (Undergraduate 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:200:679463

Pejković, Ana. "Detekcija vrhova slike." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2018. https://urn.nsk.hr/urn:nbn:hr:200:679463

Pejković, Ana. "Detekcija vrhova slike." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2018. https://urn.nsk.hr/urn:nbn:hr:200:679463

Pejković, A. (2018). 'Detekcija vrhova slike', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 03 April 2024, https://urn.nsk.hr/urn:nbn:hr:200:679463

Pejković A. Detekcija vrhova slike [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2018 [cited 2024 April 03] Available at: https://urn.nsk.hr/urn:nbn:hr:200:679463

A. Pejković, "Detekcija vrhova slike", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:200:679463

Please login to the repository to save this object to your list.
Metadata
TitleDetekcija vrhova slike
Title (english)Corner detection in images
AuthorAna Pejković
MentorIrena Galić (mentor)
MentorHrvoje Leventić (mentor)
Committee memberIrena Galić (predsjednik povjerenstva)
Committee memberZdravko Krpić (član povjerenstva)
Committee memberGoran Martinović (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 country2018-09-26, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Program Engineering
Abstract
Računalni vid i detekcije značajki za obradu slike obuhvaćaju metode za računanje apstrakcija slikovnih informacija i donošenje lokalnih odluka na svakoj točki slike, u tom trenutku postoji li neka vrsta slike određenog tipa ili ne. Dobivene značajke bit će podskupovi domene slike, često u obliku izoliranih točaka, kontinuiranih krivulja ili povezanih regija. U ovom radu je predstavljen algoritam FAST, jedan od mnogih, za detekciju i opis značajki s nekim poboljšanim svojstvima u odnosu na druge algoritme. Paralelno su provedeni eksperimenti i na ostala četiri algoritma: SIFT, SURF, ORB, BRISK radi usporedbe rezultata. Na osnovnu provedenih eksperimenata i dobivenih rezultata zaključeno je kako su značajke detektirane pomoću FAST-a kvalitetno slične ili malo bolje od ostalih metoda , ali je sam algoritam značajno brži od ostalih testiranih algoritama.
Abstract (english)
Computer vision and image detection features include methods for computing abstraction of image information and making local decisions at each image point, at which point there is a certain type of image of a particular type or not. The resulting features will be subdomains of the image domain, often in the form of isolated points, continuous curves, or related regions. This paper presents a FAST algorithm, one of many, for detecting and describing features with some improved features compared to other algorithms. Parallel experiments were performed on the other four algorithms: SIFT, SURF, ORB, BRISK for comparison of results. Based on the baseline experiments and the results obtained it was concluded that the features detected by FAST are very similar or slightly better than the other methods, but the algorithm itself is significantly faster than the other algorithms tested.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:679463
Study programmeTitle: Undergraduate University Study Programme
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2018-10-23 08:34:35