Detekcija i klasifikacija pojedinih zuba iz panoramske rendgenske snimke maloljetnika

master's thesis

• Title (english): Detection and classification of individual teeth from panoramic X-rays of minors
• Author: Marija Oreč
• Mentor: Marko Subašić (mentor)
• Committee member: Marko Subašić (predsjednik povjerenstva)
• Committee member: Tomislav Petković (član povjerenstva)
• Committee member: Juraj Petrović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-11, Croatia

Abstract

Cilj ovog rada je istražiti i implementirati metodu za detekciju i klasifikaciju pojedinih zuba iz panoramskih rendgenskih snimaka maloljetnika koristeći tehnike dubokog učenja. Prvo je proučeno područje problema te postojeće metode za detekciju i klasifikaciju objekata u slikama, s posebnim naglaskom na konvolucijske neuronske mreže. Zatim je prikupljena baza snimaka maloljetnih osoba te su konfigurirane odgovarajuće oznake vrste i lokacije pojedinog trajnog i mliječnog zuba. Implementirane su različite varijante YOLO mreže te su testirane na prikupljenim podacima uz dodatnu analizu uspješnosti za svaku grupu zubi te godine i spol osoba na slikama.

Abstract (english)

The aim of this paper is to research and implement a method for the detection and classification of individual teeth from panoramic X-ray images of minors using deep learning techniques. At first, the problem domain and existing methods for object detection and classification in images were studied, with a special emphasis on convolutional neural networks. Then, a database of X-ray images of minors was collected and appropriate annotations of the type and location of each permanent and deciduous tooth were configured. Various versions of the YOLO network were implemented and tested on the collected data, with additional performance analysis for each group of teeth, as well as the age and gender of the individuals in the images.

• Keywords: detekcija; klasifikacija; zubi; maloljetnici; neuronska mreža; yolo
• Keywords (english): detection; classification; teeth; minors; neural network; yolo
• Language: croatian
• URN:NBN: urn:nbn:hr:168:956452
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2024-10-12 21:43:29