Dental X-ray Image Segmentation using Gaussian Kernel-Based in Conditional Spatial Fuzzy C-means

Abstract

Dental X-ray image segmentation is a difficult task because of intensity inhomogeneities among various regions, low image quality due to noise and low contrast errors of data scanning. In this paper, we proposed a new conditional spatial fuzzy C-means algorithm with Gaussian kernel function to facilitate dental X-ray image segmentation. The Gaussian kernel function is used as an objective function of conditional spatial fuzzy C-means algorithm to substitute the Euclidian distance. Performance evaluation of the proposed algorithm was carried on dental X-ray from different teeth of some panoramic radiographs. The average of false negative fraction (FNF) and false positive fraction (TPF) values using proposed algorithm better than conditional spatial fuzzy C-means algorithm but vise versa for true positive volume fraction (FPF) value. The segmentation result of the proposed algorithm effectively recognizes tooth region as main part of the dental X-ray image.