Abstract
Law enforcement agencies have been exploiting biometric identifiers 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, it has become important to automate forensic identification systems. While ante mortem (AM) identification, i.e., identification prior to death, is usually possible through comparison of many biometric identifiers; postmortem (PM) identification, i.e., identification after death, is impossible using behavioral biometrics (e.g. speech, gait). Moreover, under severe circumstances, such as those encountered in mass disasters (e.g. airplane crashers) or if identification is being attempted more than a couple of weeks postmortem, most physiological biometrics may not be employed for identification, because of the decay of soft tissues of the body to unidentifiable states. Therefore, a postmortem biometric identifier has to resist the early decay that affects body tissues. Because of their survivability and diversity, the best candidates for postmortem biometric identification are the dental features.Forensic odontology is the branch of forensics that deals with human identification based on dental features. In this dissertation, we present a system for automating that process by identifying people from dental X-ray images. Given a dental image of a postmortem (PM), the proposed system retrieves the best matches from an antemortem (AM) database. The system automatically segments dental X-ray images into individual teeth and extracts representative feature vectors for each tooth; which are later used for retrieval. We developed a new method for teeth segmentation; and three different methods for representing and matching teeth. Each method has a different technique for representing the tooth shape and has its advantages and disadvantages compared with the other methods. The first method represents each tooth contour by signature vectors obtained at salient points on the contour of the tooth. The second method uses Hierarchical Chamfer distance for matching AM and PM teeth. In the third method, each tooth is described using a feature vector extracted using the force field energy function and Fourier descriptors. During retrieval, according to a matching distance between the AM and PM teeth, AM radiographs that are most similar to a given PM image, are found and presented to the user.To increase the accuracy of the identification process, the three matching techniques are fused together. The fusion of information is an integral part of any identification system to improve the overall performance. We introduce some scenarios for fusing the three matchers at the score level as well as at the fusion level.