An Application of the Curvature Scale Space Shape Descriptor for Forensic Human Identification Based on Orthopantomograms

Abstract

Part 3: Biometrics and Biometrics ApplicationsInternational audienceThis paper is devoted to the problem of forensic human identification based on the application of dental biometrics. For this purpose digital orthopantomogram images are used. The complete scheme of the approach is described. It starts with the image enhancement by means of the Laplacian pyramid decomposition. Secondly, the segmentation of an image into sub–images covering single teeth is performed. The process is based on determining the line between the upper and lower jaws by means of integral projections and, later, image intensity and types of teeth. For each obtained sub–image, covering a single tooth, its shape is extracted and the outer contour of this shape is traced. Thus, a shape descriptor can be applied in order to represent an object for the later identification. In this paper, the Curvature Scale Space algorithm is applied and investigated as one of the elements of the biometric identification approach based on digital orthopantomogram images

Human identification with dental panoramic radiographic images

“…There is no public dental panoramic dataset for comparison of the human identification methods so it is hard to make a fair comparison. To the best of author's knowledge, methods developed for panoramic dental images are [22, 23]. The method of [22] is tested on a dataset of 60 images of 30 persons and has rank‐1 accuracy of 67%.…”

“…While a panoramic X‐ray image is taken, a plastic plate is bitten to fix the head and to keep the mouth open, thus the mouth gap appears dark in the images. In this study, the mouth gap detection method similar to [14, 22] is used. The lowest value of the horizontal integral projection around the centre of the image, spatially under the highest value (which is the floor of the nasal cavity: the brightest part above the incisors), is detected as the mouth gap centre.…”

“…The term gives low values when the intensity values are low (as in the mouth gap) and provides selecting the horizontal lines that are vertically close to the last selected line. Please see [14, 22] for details.…”

“…Then, they proposed another method [8] for segmenting each tooth with the watershed algorithm. In [22], they extracted tooth contours and presented the teeth shape curvature scale space transform descriptor for matching of dental images. 60 images of 30 persons are matched with this technique and the success rate is 67%.…”

Cadaver identification with dental radiographs using isoperimetric and nodal graph approach

“…Lin et al introduced the idea of teeth numbering and classification [17] to reduce data base search time. A slightly different approach of human identification with orthopantomograms [18] was also explained in the literature. Human identification with dental panoramic radiographs is a challenging task.…”