Tooth recognition in dental radiographs via Hu's moment invariants

This paper presents a method to recognize a tooth in dental X-ray images using Hu's moment invariants. The proposed method starts with digitizing dental radiographic films. Next, rectangular bounding boxes of target teeth in the X-ray images are manually specified. The process continues with enhancing the X-ray image with histogram equalization. The teeth are segmented with the assistance of Otsu's method. The next step is to calculate Hu's moment invariants that are used as the teeth's features. Finally, tooth recognition is done by feature matching with Euclidian distance.