Dental biometrics for human identification based on dental work and image properties in Periapical radiographs

The main objective of forensic dentistry is to identify people based on their dental records, mainly as radiograph images. In this paper we attempt to present dental biometric system for preprocessing, segmentation and matching of dental image. Dental biometric system is used in forensic science, in which we need to match Postmortem (PM) radiographs with antemortem (AM) radiographs to determine the identity of the person associated with the PM image. We use a semi-automatic method to extract area, histogram features and contour of teeth from the AM and PM radiographs. We present results of extraction of tooth and dental work shape. These features are used in matching of two radiographs and based on this matching, individuals can be identified. This paper presents matching of two radiographs based on histogram properties, area of tooth and dental work. Along with these three matching techniques one more technique is used which is based on control point selection. Initial experimental results tested on small database indicate that matching of teeth based on area and contour is feasible method for human identification.