Exhaustive matching of dental x-rays 1 Journal of the Canadian Society of Forensic Science, 41(3), 2008 Exhaustive Matching of Dental X-rays for Human Forensic Identification * Maja Omanovic and Jeff J. Orchard David R. Cheriton School of Computer Science, University of Waterloo, 200 University Avenue West, Waterloo, Ontario, N2L 3G1. Canada. ABSTRACT: Dental features have been widely used for forensic identification purposes. With the large number of cases that need to be investigated by forensic odontologists, a move towards computer-aided dental identification systems is necessary. We propse an automated scoring and ranking method that can be used to augment other text-based methods such as WinID. Given a postmortem (PM) radiograph with a marked region of interest (ROI), we search the database of antemortem (AM) radiographs to retrieve a closest match. To express the degree of similarity/overlap between two radiographs, we use the weighted sum of squared differences (SSD) cost function. The method was tested on a database of 571 radiographs belonging to 41 distinct individuals. In 90% of the identification trials, our method ranked the correct match in the top 10%. In all trials, the correct match was among the top 22%. These experiments indicate that matching dental records using the SSD cost function is a viable method for human dental identification. KEYWORDS: forensic science, odontology, human identification, dental radiographs, image matching, sum of squared differences * A portion of this work was presented orally at the Conference of the Canadian Society for Forensic Science, Windsor, Canada, August 23, 2006. Funding for M. Omanovic was in the form of a Canadian Graduate Scholarship from the Natural Science and Engineering Research Council of Canada (NSERC). Funding for J. Orchard was from the NSERC Discovery Grant program.