Abstract:

Automating the process of postmortem identification of individuals using dental records is receiving increased attention. With the large number of victims encountered in mass disasters (e.g., 9/11 and Asian tsunami), automating the identification process would enhance the scalability of this process. However retrieving dental records from large databases is a very challenging task and has received inadequate attention in the literature. This paper concerns itself with the task of efficiently retrieving dental records from a database in order to assist the forensic expert in identifying deceased individuals in a rapid manner. The proposed method is a shape-based technique that consolidates the evidence presented by individual tooth contour in a dental record, i.e., it fuses tooth-to-tooth matching distances in order to render final record-to-record matching score. Experimental results indicate that the proposed approach achieves reasonable accuracy and requires significantly less time compared to the other approaches suggested in the literature thereby underscoring its relevance in real-time applications.