prikaz prve stranice dokumenta Detekcija i označavanje zuba u panoramskim rendgenskim snimkama pomoću YOLO arhitekture
No public access
undergraduate thesis
Detekcija i označavanje zuba u panoramskim rendgenskim snimkama pomoću YOLO arhitekture
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. urn:nbn:hr:168:254864
Ilić, Ivan
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Ilić, I. (2018). Detekcija i označavanje zuba u panoramskim rendgenskim snimkama pomoću YOLO arhitekture (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:254864

Ilić, Ivan. "Detekcija i označavanje zuba u panoramskim rendgenskim snimkama pomoću YOLO arhitekture." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:254864

Ilić, Ivan. "Detekcija i označavanje zuba u panoramskim rendgenskim snimkama pomoću YOLO arhitekture." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:254864

Ilić, I. (2018). 'Detekcija i označavanje zuba u panoramskim rendgenskim snimkama pomoću YOLO arhitekture', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 26 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:254864

Ilić I. Detekcija i označavanje zuba u panoramskim rendgenskim snimkama pomoću YOLO arhitekture [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2018 [cited 2024 November 26] Available at: https://urn.nsk.hr/urn:nbn:hr:168:254864

I. Ilić, "Detekcija i označavanje zuba u panoramskim rendgenskim snimkama pomoću YOLO arhitekture", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:168:254864

Metadata
TitleDetekcija i označavanje zuba u panoramskim rendgenskim snimkama pomoću YOLO arhitekture
Title (english)Detection and Classification of Teeth in Panoramic X-ray Images Using YOLO Architecture
AuthorIvan Ilić
MentorMarko Subašić (mentor)
Committee memberMarko Subašić (predsjednik povjerenstva)
Committee memberIvana Zadro (član povjerenstva)
Committee memberJelena Ivanković (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2018-07-13, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Ovaj rad predstavlja primjenu metoda dubokog učenja na zadatak detekcije i označavanja zuba u panoramskim rendgenskim snimkama. Stomatolozi u svakodnevnom radu obavljaju zadatak procjene zubnog statusa, koji uključuje određivanje svih zuba gornje i donje čeljusti. Korištenjem dubokih konvolucijskih neuronskih mreža, u kombinaciji s nadziranim učenjem, moguće je osposobiti računalo da navedeni zadatak rješava autonomno. Primjenom YOLO arhitekture zadatak lokalizacije pojedinog zuba formaliziramo kao problem regresije, a određivanje klase zuba kao problem klasifikacije. Navedeni model nakon treniranja ostvaruje rezultate od 81,15% u metrici mAP na testnom skupu, te ga osim iznimno dobre preciznosti karakterizira i velika brzina obrade snimki.
Abstract (english)
This thesis presents the application of deep learning methods for detection and classification of teeth in panoramic X-ray images. In their every day work, dentists perform dental status assessment task, which includes assessment of teeth of upper and lower jaw bone. By using deep convolutional neural networks, combined with supervised learning, it is possible to teach computer to perform this task autonomously. Using YOLO architecture we perform localization of teeth using regression and we determine the class using classification. After training, YOLO model produces mAP score of 81,15% on test set. Besides great precision, it is also characterized with great processing speed.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:254864
Study programmeTitle: 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 resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2019-03-13 20:56:26