IET BIOMETRICS, vol.7, no.4, pp.349-355, 2018 (Peer-Reviewed Journal)
Article / Article
Science Citation Index Expanded, Scopus
dentistry, support vector machines, probability, image restoration, diagnostic radiography, human identification, dental panoramic radiographic images, biometrics, 2D panoramic dental X-ray images, support vector machines, probabilistic graphical models, dental restorations, teeth restorations, tooth-wise appearance, geometric similarities, X-RAY IMAGES, CONTOUR INFORMATION, SYSTEM, BIOMETRICS, ALIGNMENT, SHAPE
Dental panoramic radiographic images are commonly used as biometrics for human identification. In this study, a novel method is presented for identifying humans by matching 2D panoramic dental X-ray images. Each tooth is first identified and labeled with support vector machines and probabilistic graphical models. Missing teeth and dental restorations are also detected. Then, matching scores between images are calculated according to tooth-wise appearance and geometric similarities by taking dental restorations into account. The method is tested on a dataset including 206 dental panoramic X-ray images of 170 different subjects. The proposed method has 81% rank-1 accuracy and 89% rank-2 accuracy.