Detekcija i klasifikacija zuba u ortopantomogramima

undergraduate thesis

• Title (english): Detection and Classification of Teeth in Orthopantomograms
• Author: Gabriela Dorić
• Mentor: Marko Subašić (mentor)
• Committee member: Marko Subašić (predsjednik povjerenstva)
• Committee member: Jelena Ivanković (član povjerenstva)
• Committee member: Denis Milošević (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2019-07-12, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Tema ovog rada je detekcija i klasifikacija zuba iz ortopantomograma, odnosno
rendgenskih slika čeljusti i zubi. Problem je riješen korištenjem Single Shot MultiBox
Detector algoritma za detekciju više objekata na slici. Mreža je trenirana i evaluirana na bazi
ortopantomograma te je pokazala solidne rezultate kao i YOLO mreža pri rješavanju istog
problem. Opisana je arhitektura Single Shot MultiBox Detectora te specifičnosti pri
treniranju SSD mreže. Navedene su prednosti SSD mreže u usporedbi sa dosadašnjim state
of the art modelima za detekciju objekata.

Abstract (english)

Main problem of this paper is detection and classification of teeth in ortophantograms
which are x-ray images that show panoramic view of jaw and teeth. The problem is solved
by using Single Shot MultiBox Detector algorithm for detection of multiple objects in image.
The network is trained and evaluated on database of orthopantomograms and it shows good
results just like YOLO network for solving the same problem. SSD arhitecture and training
process is explained. Also, SSD is compared with state of the art models for object detection.

• Keywords: Single Shot MultiBox Detector; duboke neuronske mreže; konvolucijske neuronske mreže; računalni vid; klasifikacija; regresija; SSD
• Keywords (english): Single Shot MultiBox Detector; deep neural networks; convolutional neural networks; computer vision; classification; regression; SSD
• Language: croatian
• URN:NBN: urn:nbn:hr:168:302868
• Study programme: Title: Computing; 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 resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2020-01-07 17:39:27