Performance Analysis of Various Techniques Applied in Human Identification Using Dental X-Rays

This paper proposes a novel approach for automating the analysis of identifying the person based on their ante mortem and postmortem reports. This approach involves three techniques (i.e.) morphological contour detector, Gaussian filtering and an existing semi-automatic contour extraction method. Forensic dentistry involves the identification of people based on their dental records, mainly available as radiograph images. Our goal is to automate this process using image processing and pattern recognition techniques. Given a postmortem radiograph, we search a database of antemortem radiographs in order to retrieve the closest match with respect to some salient features. In this paper, we use the contours of the teeth as the feature for matching. The algorithm completes the task in three steps: radiograph segmentation, pixel classification and contour matching. In this paper a hit rate of 0.7 is achieved by the Morphological contour detectors which are comparable with the other two methods.