Determination of unique Feature set for AM Bitewing Dental Radiographs as a Bio-metric information

Recent growth in the number of studies for automating the process of post-mortem (PM) identification of deceased individuals based on various features of teeth is remarkable. Hence, nowadays dental X-ray has played an important role in human identification. Particularly, in cases of severe accidents (Airplane crashes,9/11 bombing, Car/Train accidents), natural disasters (Asian Tsunami, Flood, Earthquake, Volcanic eruption, Typical cyclone), etc. wherein other identification clues like fingerprint, iris, face, etc. are not available for human identification. Dental features remain less invariant over longer time period. The purpose of dental image processing is to match the postmortem (PM) radiograph with the ante-mortem (AM) radiograph based on some features of the dental X-ray images. The dental radiograph images acquired may be of poor quality and contrast. Therefore, first it is important to classify and then enhance the quality of image and thereafter applied various segmentation algorithms on enhanced dental radiograph image. Various features of individual tooth are being extracted and identification can be possible based on matching of these feature vectors for PM images which are calculated and compared with AM images. This paper provides a basic idea of various classification, enhancement, segmentation and detail feature extraction techniques for human identification using dental radiographs.