prikaz prve stranice dokumenta Metode segmentacije objekata i područja u digitalnoj slici
  Download
PDF 4.43 MB
undergraduate thesis
Metode segmentacije objekata i područja u digitalnoj slici
2020. urn:nbn:hr:200:189068
Danilović, Nikola
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Communications
Chair of Multimedia Systems and Digital Television

Cite this document

Danilović, N. (2020). Metode segmentacije objekata i područja u digitalnoj slici (Undergraduate thesis). Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:189068

Danilović, Nikola. "Metode segmentacije objekata i područja u digitalnoj slici." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2020. https://urn.nsk.hr/urn:nbn:hr:200:189068

Danilović, Nikola. "Metode segmentacije objekata i područja u digitalnoj slici." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2020. https://urn.nsk.hr/urn:nbn:hr:200:189068

Danilović, N. (2020). 'Metode segmentacije objekata i područja u digitalnoj slici', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 22 April 2021, https://urn.nsk.hr/urn:nbn:hr:200:189068

Danilović N. Metode segmentacije objekata i područja u digitalnoj slici [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2020 [cited 2021 April 22] Available at: https://urn.nsk.hr/urn:nbn:hr:200:189068

N. Danilović, "Metode segmentacije objekata i područja u digitalnoj slici", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:200:189068

Islandora Bookmark - Please login to use this feature
Metadata
TitleMetode segmentacije objekata i područja u digitalnoj slici
Title (english)Methods objects and areas segmentation in a digital image
AuthorNikola Danilović
MentorSnježana Rimac-Drlje (mentor)
Committee memberSnježana Rimac-Drlje (predsjednik povjerenstva)
Committee memberZdravko Krpić (član povjerenstva)
Committee memberDrago Žagar (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Communications)
(Chair of Multimedia Systems and Digital Television)
Osijek
Defense date and country2020-09-16, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Telecommunications and Informatics
Abstract
U ovom radu opisana je teoretska podloga segmentacijskih metoda i algoritama za obradu digitalne slike te je napravljena njihova usporedba na odabranom setu problema. Obrađene segmentacijske metode su: amplitudne segmentacije, segmentacije na temelju rubova, segmentacije na temelju rasta područja i segmentacija grupiranjem. Primjena i usporedba metoda je provedena u Python programskom jeziku pomoću OpenCV programske biblioteke. Uspoređivanje se vršilo na metodama sa zajedničkim karakteristikama kako bi se istakla njihova pozitivna i negativna svojstva pri određenim uvjetima na slici. Uspoređivanjem segmentacijskih metoda došlo se do zaključka da svaka od metoda ima pozitivne i negativne karakteristike koje ovise o karakteristikama slike i vrsti problema kojeg je potrebno riješiti segmentacijom, tj. vrsti objekta ili područja kojeg je potrebno segmentirati.
Abstract (english)
This paper describes theoretical basis of segmentation methods and algorithms for digital image processing and compares them on selected set of problems. Main segmentation methods that are analysed in this paper are: thresholding, segmentation based on edge detection, segmentation based on region growing and segmentation based on clustering. Application and comparison of the segmentation methods was made using Python programming language and OpenCV library. Comparison was made on methods with common characteristics to point out their positive and negative properties in regards to the properties of the image that was being segmented. After that it was concluded that every method that was analysed had positive and negative characteristics which depended on properties of the segmented image and type of the problem that needed to be solved using a particular method.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:189068
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 on2020-11-16 13:20:46