Individual tooth segmentation in human teeth images using pseudo edge-region obtained by deep neural networks

Abstract

In human teeth images taken outside the oral cavity with a general optical camera, it is difficult to segment individual tooth due to common obstacles such as weak edges, intensity inhomogeneities and strong light reflections. In this work, we propose a method for segmenting individual tooth in human teeth images. The key to this method is to obtain pseudo edge-region using deep neural networks. After an additional step to obtain initial contours for each tooth region, the individual tooth is segmented by applying active contour models. We also present a strategy using existing model-based methods for labeling the data required for neural network training.