Segmentacija medicinskih slika korištenjem značajki teksture

undergraduate thesis

• Title (english): Medical Image Segmentation Using Texture Features
• Author: Marija Maleš
• Mentor: Sven Lončarić (mentor)
• Committee member: Sven Lončarić (predsjednik povjerenstva)
• Committee member: Jelena Ivanković (član povjerenstva)
• Committee member: Karlo Koščević (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-09-15, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

U ovom radu opisana su i programski implementirana dva načina ekstrakcije značajki teksture slike. Prva metoda je Gabor Wavelet pomoću koje obrađujemo sliku koristeći dilatirane i međusobno pomaknute Gaborove funkcije koje tvore valiće. Druga metoda je Local Binary Pattern metoda pomoću koje obrađujemo sliku uzimajući u obzir intenzitete blokova slike oko centralnih piksela. Cilj rada bio je pomoću odabranih metoda postići da računalo na temelju poznatog skupa značajki svakoga od četiri razreda upalnog tkiva transplatiranog srca može za sliku nepoznatog razreda odrediti u koji ona pripada. Obje metode pokazale su se vrlo precizne, a najbolji rezultati dobiveni su njihovom kombinacijom značajki.

Abstract (english)

In this thesis are described and implemented two methods of extracting textural features of image. First method is Gabor Wavelet which processes image by using dilatated and mutually shifted Gabor's functions, thus creating wavelets. Second method is Local Binary Pattern method which processes image by considernig blocks of intensity around central pixels. The aim of this theasis was to achieve that computer can determine and classificate the inflammatory degree of an unknown image by using selected methods based on known features specific for every degree of inflammatory heart tissue. Both methods were precise, but best results were collected by using combination of them.

• Keywords: obrada slike; značajke teksture; Gabor Wavelet; Local Binary Pattern; klasifikatori; strojno učenje; slike biopsije srca; upalni razredi
• Keywords (english): image processing; texture features; Gabor Wavelet; Local Binary Pattern; classificators; machine learning; heart biopsy images; inflammatiory tissue degrees
• Language: croatian
• URN:NBN: urn:nbn:hr:168:121867
• Study programme: Title: Electrical Engineering and Information Technology; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 08:29:19