Person Identification by Dental Images using Striae Patterns
he Identification of people using their dental records, mainly as radiograph images searches the database of Postmortem (PM) and antemortem (AM) radiographs to determine the identity of the person associated with the PM image. We use a semi-automatic method to extract shapes of the teeth from the AM and PM radiographs, and find the affine transform that best fits the shapes in the PM image to those in the AM images. A ranking of matching scores is generated based on the distance between the AM and PM tooth shapes.
A manual comparison between the AM and PM records is based on a systematic dental chart completed by some forensic experts In this chart, a number of distinctive features are noted for each tooth individually. These features include properties of the teeth (e.g., tooth present/not present, crown and root morphology and pathology and dental restorations), periodontal tissue features, and anatomical features.
Depending on the number of matches, the forensic expert rejects or confirms the tentative identity. Unlike other biometric characteristics (e.g., fingerprints, iris, etc.), dental identification is complicated by the fact that dental features do change over time. The teeth can change appearance, or can be missing altogether, as a result of dental work or accidents occurring after the AM records are taken.
In fact, for this very reason, although accepted in a court of law, dental based identification is considered less reliable than other biometric methods. But in certain cases (e.g., victims in a major fire), this may be the only available biometric method. From a pattern recognition and computer vision standpoint, the problem of person identification based on dental records can be cast as an image matching and retrieval problem: given a dental image (usually a PM radiograph), we must search the database to find an AM radiograph that best matches with this PM record.
2. Existing Method:
The Identification is done in two Modules:
1. The shape extraction module extracts the shapes of the teeth in the database radiographs and query images.
2. The matching module matches the shapes from the query image to those from the database images.
Then a ranking is produced to show the best matching(s) in the database. The matching is performed in three steps. In the first step, a shape registration method is proposed to align and compute the distance between two teeth on the basis of tooth contours. If the shapes of the dental work are available, they can assist in the matching. An area-based metric is done for matching the dental work. The two matching distances are then combined to obtain the tooth correspondence and to measure the similarity between images. Possible matches for the PM images are identified from a database of AM images. The labels of the retrieved images are used to establish the identity of the deceased subject.
However, in some cases, it is difficult to apply the above method because the images are very blurred, or the query shape is partially occluded so there is not enough information available to characterize the teeth. There are still a number of challenges need to overcome. The shape extraction is a difficult problem for dental radiographs, especially for poor quality images where some tooth contours are indiscernible.
For the subjects with a number of missing teeth, other features such as the shape of mandibular canals and maxillary sinus, for subject identification.
4. Proposed Method:
Fortunately, the radiographs not only give us the information about the shape of the teeth, but also other information such as the artificial prothesis of the teeth, the striae patterns and trabecular patterns developing an image restoration algorithm to handle poor quality radiographs.
Striae is also a general term referring to thin, narrow groove or channel, or a thin line or band especially if several of them are parallel or close together. Fourier analysis provides a more general approach for detecting the frequency and orientation of the striae patterns, and is more suitable for the purpose given the range of possible frequencies and orientations.
Apart from knowing the striae orientation and frequency, the borders of the central area of the diatom with no striae (the sternum or raphe-sternum) should be detected.
The proposed format is to work similar to the synthesis algorithm of diatoms where the striae are formed gradually, the ones near the centre of the diatom start growing first and may be partially completed by the time the striae further away from the centre start forming. The attempt is to model this process similar to iterative synthesis algorithm of diatom. The unique nature of our dental anatomy and the placement of custom restorations ensure accuracy when the techniques are correctly employed.
1. Anil K. Jain, Hong Chen, and Silviu Minut, “Dental Biometrics: Human Identification Using Dental Radiographs”
2. Y.Hicks, D.Marshall, R.R.Martin, P.L.Rosin S.Droop, D.G.Mann, “Building Shape And Texture Models Of Diatoms For Analysis And Synthesis Of Drawings And Identification”.
3. Hong Chen and Anil K. Jain, “Dental Biometrics: Alignment and Matching of Dental Radiographs”.
4. Forensic Odontology News
5. Diaa Eldin M. Nassar and Hany H. Ammar, A Prototype Automated Dental Identification System (ADIS)
Article name: Person Identification by Dental Images using Striae Patterns essay, research paper, dissertation