Određivanje značajki oblika zuba za procjenu godina starosti iz panoramske rendgenske snimke

undergraduate thesis

• Title (english): Teeth shape feature extraction for age estimation using panoramic x-ray images
• Author: Mia Tomaić
• Mentor: Marko Subašić (mentor)
• Committee member: Marko Subašić (predsjednik povjerenstva)
• Committee member: Tomislav Petković (član povjerenstva)
• Committee member: Nikola Banić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2017-02-24, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovome radu prikazana je primjena Matlabovog alata ASM (Active Shape Model) te njegova prilagodba za rad na kruni donjeg lijevog umnjaka. Objašnjena je uporaba alata Gimp za označavanje dijelova zuba potrebnih za izradu modela oblika te izdvajanje istih pomoću slojeva. Objašnjena je sama izrada modela te njegova primjena na skupu slika za treniranje te na skupu testnih slika. Detaljno je opisan rad modela oblika prilikom određivanja optimalnog položaja za svaku točku modela. Dana su dva načina ispitivanja točnosti rada modela te su prikazani rezultati za različite rezolucijske skale i to za oba skupa slika. Prikazana je izrada neuronske mreže, objašnjen je njen rad te određivanje broja skrivenih slojeva. Dana je procjena starosti pomoću dvije neuronske mreže te je ispitana točnost procjene istih.

Abstract (english)

This work shows how to use and adjust Matlab Active Shape Model (ASM) to work with crown of a left bottom wisdom tooth. We have explained how to use Gimp for marking and exporting important layers of tooth. This work gives detail explanation for building shape model and his usage on both training and test images. There is, also, given clarification how model works and how optimal position for every model point is determined. We showed two different ways of testing model work for several resolution scales and gave results for both sets of images. Finally, there is given explanation how to build artificial neural network in Matlab, how to determine number of hidden layers and description how neural network works. We gave age estimation with two neural networks and showed results of their work.

• Keywords: Gimp; Matlab; ASM; model oblika; PCA analiza; kruna umnjaka; rendgenska snimka; segmentacija; rezolucijska skala; false positive i false negative postoci; Euklidska udaljenost; neuronska mreža; srednja kvadratna pogreška
• Keywords (english): Gimp; Matlab; ASM; shape model; PCA analysis; wisdom tooth crown; x-ray image; segmentation; resolution scale; false positive and false negative percentages; Euclidean distance; neural network; the mean square error
• Language: croatian
• URN:NBN: urn:nbn:hr:168:925850
• 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: 2019-03-14 01:34:51