Teeth/Palate and interdental segmentation using artificial neural networks

Authors:
Kelwin Fernandez;Carolina Chang
Affiliations:
Grupo de Inteligencia Artificial, Universidad Simón Bolívar, Caracas, Venezuela;Grupo de Inteligencia Artificial, Universidad Simón Bolívar, Caracas, Venezuela
Venue:
ANNPR'12 Proceedings of the 5th INNS IAPR TC 3 GIRPR conference on Artificial Neural Networks in Pattern Recognition
Year:
2012

Citing 9
Cited 0

Computer Vision

Computer Vision
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
Effiicient BackProp

Neural Networks: Tricks of the Trade, this book is an outgrowth of a 1996 NIPS workshop
Digital Image Processing (3rd Edition)

Digital Image Processing (3rd Edition)
A neural network system for matching dental radiographs

Pattern Recognition
An effective classification and numbering system for dental bitewing radiographs using teeth region and contour information

Pattern Recognition
Contrast enhancement of color images based on Wavelet Transform and human visual system

GVE '07 Proceedings of the IASTED International Conference on Graphics and Visualization in Engineering
Automatic segmentation of color lip images based on morphological filter

ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part I
Handbook of Metaheuristics

Handbook of Metaheuristics

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a computational system that combines Artificial Neural Networks and other image processing techniques to achieve teeth/palate segmentation and interdental segmentation in palatal view photographs of the upper jaw. We segment the images into teeth and non-teeth regions. We find the palatal arch by adjusting a curve to the teeth region, and further segment teeth from each other. Best results to detect and segment teeth were obtained with Multilayer Perceptrons trained with the error backpropagation algorithm in comparison to Support Vector Machines. Neural Networks reached up to 87.52% accuracy at the palate segmentation task, and 88.82% at the interdental segmentation task. This is an important initial step towards low-cost, automatic identification of infecto-contagious oral diseases that are related to HIV and AIDS.