Triangular geometry-based novel feature and a novel algorithm for human identification using dental radiographs

Abstract

Dental X-ray has played an important role in identification of missing or unidentified persons. Particularly in cases where other identification clues like fingerprint, iris, etc. are not available and, moreover, dental features remain more or less invariant over time. The purpose of dental image processing is to match the Post-mortem (PM) radiograph with the Antemortem (AM) radiograph based on some unique feature of the radiograph. The first step is to enhance the quality of image and region of interest can be separated. Unique features of a tooth are extracted and identification is performed based on matching of these feature vectors of PM images with those of AM images available in the database. A new feature based on triangular geometry of the tooth has been proposed and thereafter matching of query and database images is performed for identification of the subject. This feature is called the tooth taper parameter.