DocumentCode :
2224085
Title :
Classification and numbering of posterior teeth in bitewing dental images
Author :
Aeini, Faraein ; Mahmoudi, Fariborz
Author_Institution :
Comput. Dept., QIAU (Qazvin Islamic Azad Univ.), Qazvin, Iran
Volume :
6
fYear :
2010
fDate :
20-22 Aug. 2010
Abstract :
The purpose of forensic dentistry is to identify individuals based on their dental characteristics. In this paper, a methodology to classify and assign numbers to teeth in bitewing dental images is presented. The goal is to using the result of this methodology in an automated dental identification system. In this way, proposed approach benefits of categorizing molar and premolar teeth and also spatial relations between teeth in jaws. The three main steps in the methodology are: 1. Deducing the exact location and size of the mesiodistal neck for each type of teeth. 2. Teeth classification using a linear model and 3. Identification of types and numbers of the missing and/or broken teeth. This methodology enables us to assign numbers to the remaining teeth using the universal number system. Experimental result obtained for this investigation on a database of 476 teeth, indicate that the proposed methodology is more advanced in neck detection, teeth classification and numbering, broken teeth detection, identification of the number and type of missing teeth in comparison with some previously published work.
Keywords :
dentistry; forensic science; image classification; medical image processing; automated dental identification system; bitewing dental images; broken teeth detection; forensic dentistry; linear model; neck detection; posterior teeth classification; posterior teeth numbering; universal number system; Teeth; broken teeth detection; classification and numbering of teeth; dental identification; mesiodistal crown; mesiodistal neck; missing teeth detection;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Advanced Computer Theory and Engineering (ICACTE), 2010 3rd International Conference on
Conference_Location :
Chengdu
ISSN :
2154-7491
Print_ISBN :
978-1-4244-6539-2
Type :
conf
DOI :
10.1109/ICACTE.2010.5579369
Filename :
5579369
Link To Document :
بازگشت