prikaz prve stranice dokumenta Lokalizacija vidnog polja u slikama s mikroskopa
  Download
PDF 1.46 MB
undergraduate thesis
Lokalizacija vidnog polja u slikama s mikroskopa
2023. urn:nbn:hr:200:187981
Štern, Dora
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

Štern, D. (2023). Lokalizacija vidnog polja u slikama s mikroskopa (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:200:187981

Štern, Dora. "Lokalizacija vidnog polja u slikama s mikroskopa." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:187981

Štern, Dora. "Lokalizacija vidnog polja u slikama s mikroskopa." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:187981

Štern, D. (2023). 'Lokalizacija vidnog polja u slikama s mikroskopa', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 20 April 2024, https://urn.nsk.hr/urn:nbn:hr:200:187981

Štern D. Lokalizacija vidnog polja u slikama s mikroskopa [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2023 [cited 2024 April 20] Available at: https://urn.nsk.hr/urn:nbn:hr:200:187981

D. Štern, "Lokalizacija vidnog polja u slikama s mikroskopa", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:200:187981

Please login to the repository to save this object to your list.
Metadata
TitleLokalizacija vidnog polja u slikama s mikroskopa
Title (english)Localization of the field of view in microscope images
AuthorDora Štern
MentorHrvoje Leventić (mentor)
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 country2023, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Data Processing
Abstract
Ideja ovog završnog rada bila je razviti programsko rješenje za lokalizaciju kvadranata na slikama s mikroskopa. Ovaj proces uobičajeno se radi ručno pa u slučaju kada ima puno slika, može potrajati. Metoda je razvijena koristeći programski jezik Python i biblioteku za računalni vid OpenCV. Ova biblioteka omogućava pred-obradu slike, segmentaciju, otkrivanje rubova i kontura na slici. Kako bi se slika pred-obradila za analizu, potrebno ju je normalizirati, ukloniti šum, izdvojiti prednji plan i pozadinu. Nakon što se izdvoji prednji plan slike, primjenjuje se algoritam za pronalaženje linija. Linije na slici definiraju zatvorene oblike koji se detektiraju algoritmom za pronalazak kontura. Krivulje se mogu svesti na minimalan broj točaka, a metoda traži one s 4 točke tj. pravokutnike. Pravokutnici se tada odvajaju od kvadrata koji služe za određivanje lokacije samog kvadranta na slici. Brojanjem kontura na svakoj strani kvadranta, kvadrant se lokalizira s obzirom na dvije strane koje imaju najviše pravokutnika. Testiranjem metode utvrđeno je da metoda jako ovisi o pred procesiranju i ne može točno odrediti kvadrant ako nisu postignuti traženi uvjeti.
Abstract (english)
The aim of this paper was to develop a software solution for quadrant localization on microscope images. This process is usually done by hand so in case of greater number of images, this process could take a while. The method was developed using Python programming language and computer vision library OpenCV. This library enables image pre-processing, segmentation, edge detection and contour detection. To prepare the image for analysis, it should be normalized, noise should be removed, foreground and background segmented, and line detection algorithm applied. Lines on the image define closed contours which are detected with a contour detection algorithm. Contours can be reduced to a minimal number of points, and the method searches the ones with four points i.e. rectangles. Rectangles are then separated from squares that are used to determine the location of the quadrant in the image. Counting the number of contours on each side of the quadrant, the quadrant is localized based on two sides which have the most rectangles. While testing the method, it was determined that it strongly depends on pre-processing and the quadrant can't be localized correctly if the needed conditions aren't met.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:187981
Study programmeTitle: Undergraduate University Study Programme in Computer Engineering
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2023-10-19 16:26:56