Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/49146
Title: Study and Development of Techniques for 3D Dental Identification
Authors: ZHONG XIN
Keywords: 3D dental identification, feature extraction and matching, pattern recognition, medical image processing, computational geometry, dental biometrics
Issue Date: 16-Aug-2013
Source: ZHONG XIN (2013-08-16). Study and Development of Techniques for 3D Dental Identification. ScholarBank@NUS Repository.
Abstract: Dental records have been regarded as one of the primary identifiers from recovered remains under severe conditions and mass disasters when other biological identifiers cannot be obtained. The commonly used approach is through manual comparison of dental features in dental charts and radiographs, which is inefficient and prone to errors. The primary objective of this thesis is to develop computer-based 3D identification approaches that overcome key hurdles in those based on 2D radiographs, including inaccurate tooth feature extraction from blurred images and the incorrect matching due to differences of imaging angles since radiographs are 2D projections of 3D objects. Three approaches are proposed and investigated: point-based matching and identification, arch-based matching and identification, and single-tooth classification and identification. The developed methods are suitable for computer-facilitated decision support dental identification. The identification of partial dental sets, noisy sets and single tooth is feasible in 3D, with certain limitations that are discussed.
URI: http://scholarbank.nus.edu.sg/handle/10635/49146
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
ZhongX.PDF.pdf6.77 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

171
checked on Feb 16, 2018

Download(s)

294
checked on Feb 16, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.