Enhanced Human Identification System using Dental Biometrics

This paper presents a Dental Based Security System (DBSS), proves to be an equivalent alternative to the Thumb Impression Based Security System (TIBSS) for identifying the persons. The Enhanced Human Identification System using Dental Biometrics (EHISDB) enable content-based retrieval of antemortem (AM) images from the database by comparing the similarity of teeth to postmortem (PM) images. During storage, the system classifies the dental image to upper periapical and lower periapical views using horizontal and vertical edges. It then segments the teeth and the bones in the periapical view images, using statistical and geometrical calculations, given as an input to the neural networks stored in the database for comparison with postmortem images. Experiments on a small database show that our method is effective for dental image classification and teeth segmentation, provides good results for feature extraction, and acts as a good tool for human identification.