Tooth Point Cloud Segmentation of Dental Model Based on Region Growing

Abstract

Single tooth segmentation is an important technique for computer-assisted orthodontic restoration. Aiming at the problem of interdental region fusion in digital 3D dental model and the limitations of traditional tooth segmentation methods such as complex interactive operations and high manual interference, a tooth point cloud segmentation method based on region growing is proposed. First, the curvature information is used to identify and extract the Gum-tooth boundary feature area, and the points of the gum area and the tooth area are segmented by the region growing method. Then, the local distribution density is used to extract the interdental fusion region, and any point of each tooth is selected as the seed point for region growing. Finally, the point cloud segmentation result of each tooth is obtained. The experimental results show that the proposed algorithm can effectively reduce manual intervention and realize the point cloud segmentation of each tooth of the dental model more accurately.