Classification and Numbering of Dental Radiographs for an Automated Human Identification System

Abstract

 Dental based human identification is commonly used in forensic. In a case of large scale investigation, manual identification needs a large amount of time. In this paper, we developed an automated human identification system based on dental radiographs. The system developed has two main stages. The first stage is to arrange a database consisting of labeled dental radiographs. The second stage is the searching process in the database in order to retrieve the identification result. Both stages use a number of image processing techniques, classification methods, and a numbering system in order to generate dental radiograph’s features and patterns. The first technique is preprocessing which includes image enhancement and binarization, single tooth extraction, and feature extraction. Next, we performed dental classification process which aims to classify the extracted tooth into molar or premolar using the binary support vector machine method. After that, a numbering process is executed in accordance with molar and premolar pattern obtained in the previous process. Our experiments using 16 dental radiographs that consist of 6 bitewing radiographs and 10 panoramic radiographs, 119 teeth objects in total, has shown good performance of classification. The accuracy value of dental pattern classification and dental numbering system are 91.6 % and 81.5% respectively.