Automated Dental Identification with Lowest Cost Path-Based Teeth and Jaw Separation

Abstract

Abstract:Teeth are some of the most resilient tissues of the human body. Because of their placement, teeth often yield intact indicators even when other metrics, such as finger prints and DNA, are missing. Forensics on dental identification is now mostly manual work which is time and resource intensive. Systems for automated human identification from dental X-ray images have the potential to greatly reduce the necessary efforts spent on dental identification, but it requires a system with high stability and accuracy so that the results can be trusted. This paper proposes a new system for automated dental X-ray identification. The scheme extracts tooth and dental work contours from the X-ray images and uses the Hausdorff-distance measure for ranking persons. This combination of state-of-the-art approaches with a novel lowest cost path-based method for separating a dental X-ray image into individual teeth, is able to achieve comparable and better results than what is available in the literature. The proposed scheme is fully functional and is used to accurately identify people within a real dental database. The system is able to perfectly separate 88.7% of the teeth in the test set. Further, in the verification process, the system ranks the correct person in top in 86% of the cases, and among the top five in an astonishing 94% of the cases. The approach has compelling potential to significantly reduce the time spent on dental identification. Keywords:Path-finding, Human dental identification 44Copyright© Holstad Grafisk, Oslo -Print: prografia, Oslo -ISSN 1503-9552 FORENSIC SCIENCE Scandinavian journal of Nordisk rettsmedisinThe new separation method has the benefit of being able to recover from poor starting conditions, making it robust in cases where the teeth in the image are severely rotated or oddly shaped. A. Problem StatementThe ultimate goal of this work is to create an improved ADIS with new innovative methods as well as methods from related research. As part of the path towards this goal a few hypotheses will be tested. These can be listed as follows.1) It is possible to identify the persons in the data set using only tooth and dental work contour information extracted from the dental X-ray images.The particular combination of techniques and methods applied in this work has not been used to solve this problem before. This hypothesis helps find how the whole system performs with regards to ranking and retrieval accuracy.2) Pathfinding can be used effectively for separating teeth and jaws in dental X-ray images.The separation of dental X-ray images into smaller images each containing a single tooth is a significant problem during feature extraction from such images. B. OutlineFollowing the introduction, section II describes the previous work in the field. The proposed approach is presented in sec-tion III. Testing of both the new method and the methodology as a whole, with discussion, can be found in section IV. Subsequently, the conclusion is presented with a few thoughts on further work.

Automatic human identification based on dental X-ray radiographs using computer vision

“…Nevertheless, the matching process is based on small image details. Very large changes of teeth or dental works can complicate identification, e.g., where the shapes of the teeth have changed due to artificial prostheses, tooth growth or tooth extraction 9,[36][37][38][39] . Furthermore, the unsuccessful identifications can possibly result from inferior image quality 3,6 .…”

Forensic Odontology: Automatic Identification of Persons Comparing Antemortem and Postmortem Panoramic Radiographs Using Computer Vision

“…The mismatched results were mainly due to inaccurate contours caused by poor image quality [8 -13] or because the shapes of the teeth changed due to artificial prosthesis, tooth growth, and tooth extraction [8 -10, 12, 13]. Further reasons were a different viewing angle on bitewing images [12] or a translation offset in the image [13]. In [14,15] the segmentation result had to be corrected manually, this method is not suitable for large databases.…”

“…The databases included 93 to 187 antemortem bite-wing images. Ølberg et al [13] combined methods for the extraction of tooth and dental work contours from PR and used the Hausdorff-distance measure for ranking persons. The database included 67 persons.…”

Specific oral and maxillofacial identifiers in panoramic radiographs used for human identification

“…Additionally, with the improvement in recent technology, many researchers have investigated the method of tooth recognition on radiographic images through deep learning of artificial intelligence [15,16]. Therefore, the applicability and usefulness of outcomes in coding and data matching systems should also be taken into consideration.…”

“…Another approach is to compare PM to AM dental radiographs by dental identifiers [7,12]. Several computer-aided matching systems have been presented that use tooth contours, dental restoration shape, and automatic identification [13][14][15][16]. The frontal sinus and nasal septum can also act as useful indicators for personal identification because of their uniqueness in individuals.…”