By Topic

Application of vector quantization algorithm to dental arch classification in orthodontics practice

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Qian-Rong Gu ; Dept. of Electron. Eng., Univ. of Tokyo, Japan ; T. Shibata ; K. Fujita ; K. Takada

Classifying dental arch forms of human adults with normal occlusions into a set of typical patterns objectively and quantitatively has an important meaning in orthodontics practice. In this paper, vector quantization (VQ) method with generalized Lloyd algorithm is applied to classify dental arch forms for two purposes: 1) reproduce the classification results categorized by experienced dentists; and 2) classify the dental arch forms objectively and quantitatively. We found that dentists pay more attention to the third and forth teeth from the front than the others when they do the classification. By increasing the weights of these two teeth, VQ can archive a classification result 95% same as the one categorized by the experienced dentists. When the weights of all teeth are set to the same value, the classification results of VQ are better than the dentist's with respect to VQ error. Though, increase of pattern numbers follows a decrease in VQ error, classifying the dental arches into four patterns can get a maximal reduction in VQ error, i.e. has the best performance-cost ratio.

Published in:

Automation Congress, 2002 Proceedings of the 5th Biannual World  (Volume:13 )

Date of Conference: