Abstract
Law enforcement agencies have exploited biometrics for decades as key tools in forensic identification. With the evolution in information technology and the huge volume of cases that need to be investigated by forensic specialists, automating the process of forensic identification became inevitable. Postmortem (PM) identification, encountered in mass disasters (e.g. natural disasters, plane crashes, etc), requires use of biometric characteristics that resist early decay of body tissues as well as withstand severe conditions. To this end, dental features are the best candidates for PM identification [1]. In 1997, the Criminal Justice Information Services (CJIS) division of the FBI created a Dental Task Force (DTF) to foster the creation of an Automated Dental Identification System (ADIS). ADIS will provide automated search and matching capabilities for digitized radiographs and photographic images, so as to come with a short match list for dental forensic experts. Research teams from West Virginia University (WVU), Michigan State University (MSU), and University of Miami (UM), in coordination with CJIS, are collaboratively developing a research prototype of ADIS. Creating ADIS is a question of providing a highly automated environment that integrates efficient image processing and pattern recognition techniques thus achieving both high accuracy and timeliness. To this end, we are not only looking at automating the steps followed by forensic experts to examine dental radiographs of subjects and compare them against those of missing or unidentified persons. But we are also looking at intelligent analysis of radiographs in order to utilize underlying image structures that are often difficult to be assessed merely by visual examination [2].