Forensic identification system using dental panoramic radiograph

Abstract

Forensic odontology is one method of determining the identity of the individuals who use it as a base dental identification. Teeth can provide information about the individual's identity because of its distinctive. Currently, the process of forensic identification through dental radiography is performed manually so it took a long time to match the teeth with human identity. Therefore, we need a system that can identify human identity quickly and accurately through dental radiography. In this experiment develop a system to identify human identity through dental radiography image quickly and accurately. The method of active shape model used for segmentation of mandibular teeth, this method can do shape search, to get the most appropriate shape. So that will get contours in accordance with the desired contour. This can help provide great results for the next stage. Then the extraction method used is Hu moment invariant, from this stage we will get 7 values that are free of rotation and scaling, so later if there is radiography that occurs the shift will still be detected. This experiment used 20 training data for segmentation, and 75 data dental radiograph images that has different shift for matching stage. The results of this research show success with an average of 82.67%. The proposed research method for this forensic identification system can be an appropriate system for the process of identifying a person based on dental radiography images.