prikaz prve stranice dokumenta Programsko rješenje filtra za detekciju rubova na slici
  Download
PDF 3.65 MB
master's thesis
Programsko rješenje filtra za detekciju rubova na slici
Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2023. urn:nbn:hr:235:095392
Gubec, Sandra
University of Zagreb
Faculty of Mechanical Engineering and Naval Architecture

Institutional repository: Repository of Faculty of Mechanical Engineering and Naval Architecture University of Zagreb

Cite this document

Gubec, S. (2023). Programsko rješenje filtra za detekciju rubova na slici (Master's thesis). Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:235:095392

Gubec, Sandra. "Programsko rješenje filtra za detekciju rubova na slici." Master's thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2023. https://urn.nsk.hr/urn:nbn:hr:235:095392

Gubec, Sandra. "Programsko rješenje filtra za detekciju rubova na slici." Master's thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2023. https://urn.nsk.hr/urn:nbn:hr:235:095392

Gubec, S. (2023). 'Programsko rješenje filtra za detekciju rubova na slici', Master's thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, accessed 11 August 2024, https://urn.nsk.hr/urn:nbn:hr:235:095392

Gubec S. Programsko rješenje filtra za detekciju rubova na slici [Master's thesis]. Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture; 2023 [cited 2024 August 11] Available at: https://urn.nsk.hr/urn:nbn:hr:235:095392

S. Gubec, "Programsko rješenje filtra za detekciju rubova na slici", Master's thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:235:095392

Metadata
TitleProgramsko rješenje filtra za detekciju rubova na slici
Title (english)Program solution of the filter for detecting edges in the image
AuthorSandra Gubec
MentorTomislav Stipančić (mentor)
GranterUniversity of Zagreb
Faculty of Mechanical Engineering and Naval Architecture
Zagreb
Defense date and country2023-12-07, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Mechanical Engineering
Abstract
U doba digitalne obrade slika, primjena postupaka filtriranja ima značajnu ulogu u poboljšanju i manipulaciji slikama sa svrhom izvlačenja korisnih informacija i unaprjeđenja njihove vizualne kvalitete. Filtriranje se odvija u dvije domene, prostornoj i frekvencijskoj. Filtriranje u prostornoj domeni izravno utječe na vrijednosti piksela, dok se filtriranje u frekvencijskoj domeni temelji na Fourierovoj transformaciji. Iako različitog pristupa, obje tehnike imaju jednake zadatke – izoštravanje, zaglađivanje, smanjenje šuma te detekcija rubova na slici. Rubovi su nositelji informacija o strukturi i granicama objekata na slici. Definiraju oblike te pomažu pri prepoznavanju objekata. Detekcija rubova također se izvodi u prostornoj i frekvencijskoj domeni. U prostornoj domeni ona se temelji na upotrebi operatora gradijenta koji ističu područja nagle promjene intenziteta što ukazuje na prisutnost ruba. U frekvencijskoj domeni koriste se visokopropusni filteri kako bi se istaknule visokofrekventne komponente koje su karakteristične rubovima. Detekcija rubova značajna je u područjima medicinske dijagnostike, računalnog vida te sigurnosnih sustava.
Abstract (english)
In the era of digital image processing, the application of filtering procedures plays a significant role in improving and manipulating images to extract useful information and enhance their visual quality. Filtering occurs in two domains: spatial and frequency. Spatial domain filtering directly influences pixel values, while frequency domain filtering is based on Fourier transformation. Despite different approaches, both techniques have identical purpose – sharpening, smoothing, noise reduction, and edge detection in images. Edges are carriers of information about the structure and boundaries of objects in the image. They define shapes and help to recognize objects. Edge detection is performed in both spatial and frequency domains. In the spatial domain, it relies on the use of gradient operators that highlight areas of abrupt intensity changes, indicating the presence of an edge. In the frequency domain, high-pass filters are used to emphasize high-frequency components characteristic of edges. Edge detection is significant in areas such as medical diagnostics, computer vision, and security systems.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:235:095392
Study programmeTitle: Mechanical Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka strojarstva (magistar/magistra inženjer/inženjerka strojarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2023-12-04 10:04:56