Segmentation of dental radiograph images

Abstract

Dental biometrics is another authentication technique where the dental features are used from dental images for identify a person. Segmentation of teeth from dental radiograph images is a crucial step for achieving automated forensic identification. Segmentation of teeth helps a dentist to diagnose the teeth problems and understand the structure of the teeth. The dental segmentation work we discuss in the paper is based on Otsu's thresholding and connected component analysis. Initially we input a radiograph image of teeth. Preprocessing is done using the smoothening filter to remove the noise or the corrupted pixels in the dental image. We perform dental segmentation in periapical dental images. We preprocess the image for noise removal and enhancement is done using CLAHE. Finally, Segmentation is done by Otsu's thresholding and the connected component are identified to extract the ROI of the teeth is segmented.