Please use this identifier to cite or link to this item:
Title: Computer-aided cephalometric landmark identification
Authors: YANG MEI
Keywords: cephalometrics, automatic, landmarking, wavelet, neural network, genetic algorithms.
Issue Date: 20-Aug-2004
Citation: YANG MEI (2004-08-20). Computer-aided cephalometric landmark identification. ScholarBank@NUS Repository.
Abstract: For the purpose of making head measurements, cephalometrics makes use of characteristic reference points in term of landmarks to characterize the geometry of the skull. Locating landmarks manually is tedious and repeating. Therefore, the motivation exists to automate this process. We employ wavelet decomposition as the feature extraction technique, and a neural network and genetic algorithms as the search technique to develop a 2-D automatic landmark detection method. Ten lateral view cephalograms were used to test our 2-D automatic landmarking method. The detection results have confirmed the effectiveness of this method. 3-D cephalometry makes use of two projections of cephalograms to compute 3-D cephalometric landmark positions. In this study, we use the lateral and posteroanterior projection cephalograms to develop our 3-D landmarks position computation method. Our experiment on 3-D landmark position computation shows that 3-D cephalometry should be realized on cephalograms that all acquired simultaneously in exact orthogonal positions.
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
YangMei_HT016610N_thesis.pdf3.65 MBAdobe PDF



Page view(s)

checked on Dec 16, 2018


checked on Dec 16, 2018

Google ScholarTM


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