Extraction of Teeth Shapes from Orthopantomograms for Forensic Human Identification

Frejlichowski, Dariusz; Wanat, Robert

doi:10.1007/978-3-642-23678-5_6

Cited by 12 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the studies in the literature (Jain et al, 2003;Abdel-Mottaleb et al, 2003;Zhou and Abdel-Mottaleb, 2005) directly use the intensity values via histogram projection in order to detect the teeth. However, in panoramic images the gap between the teeth disappears and occlusions may occur because of stitching partial X-ray images taken from the circular shaped jaw onto a 2-D image (Frejlichowski and Wanat, 2011). Therefore, instead of detecting the teeth with intensity change information, we propose using the textural and intensity descriptors together without requiring a model for each tooth.…”

Section: Tooth Detection Modulementioning

confidence: 99%

“…It is tested on both bitewing and panoramic images; but, the system is semi-automatic. The system in (Jain et al, 2003) eliminates the inaccurate segmentation lines using the dental pulp which is also utilized in (Frejlichowski and Wanat, 2011) instead of the gaps between the teeth for separating the adjacent teeth. In (Lin et al, 2010), the SVM classifier runs with several geometrical tooth features to classify a tooth.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Tooth Identification in Dental Panoramic Images with Atlas-based Models

Guzel

Oktay

Tufan

2015

Proceedings of the International Conference on Pattern Recognition Applications and Methods

View full text Add to dashboard Cite

After catastrophes and mass disasters, accurate and efficient identification of decedents requires an automatic system which depends upon strong biometrics. In this paper, we present an automatic tooth detection and labeling system based on panoramic dental radiographs. Although our ultimate objective is to identify decedents by comparing the postmortem and antemortem dental radiographs, this paper only involves the tooth detection and the tooth labeling stages. In the system, the tooth regions are first determined and the detection module runs for each region individually. By employing the sliding window technique, the Haar features are extracted from each window and the SVM classifies the windows as tooth or not. The labeling module labels the candidate tooth positions determined by the SVM with an atlas-based model and the final tooth positions are inferred. The novelty of our system is combining the atlas-based model with the SVM under the same framework. We tested our system on 35 panoramic images and the results are promising.

show abstract

Section: Tooth Detection Modulementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic Tooth Identification in Dental Panoramic Images with Atlas-based Models

Guzel

Oktay

Tufan

2015

Proceedings of the International Conference on Pattern Recognition Applications and Methods

View full text Add to dashboard Cite

show abstract

“…where M is the upper limit for linear enhancement and G is the constant gain. In our previous experiments [13,16,17] the best results were obtained when using the following combination of methods: 1) the averaging of the two Laplacian pyramid layers next to last, 2) unsharp filter on the second layer, 3) contrast enhancement, based on the eq. 2-3.…”

Section: Image Enhancement Segmentation and The Extraction Of Teeth mentioning

confidence: 99%

“…During the segmentation process the integral projections [15,16] or active contour models [12] have been applied so far. The extraction of particular teeth shapes is performed using active shapes [14], line scanning [15] or watersheds [17]. The first two algorithms were developed specifically for the intraoral images.…”

Section: Introductionmentioning

confidence: 99%

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

Frejlichowski

Czapiewski

2013

Computer Information Systems and Industrial Management

Self Cite

View full text Add to dashboard Cite

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

show abstract

“…Then, the labels of the teeth are determined using the spatial relationships between the teeth. The system presented in [7] implements the watershed algorithm to segment the panoramic images into small regions and runs a fitness function with a set of features of each region for tooth detection. In the study of [3], support vector machines are used with several geometrical properties of the teeth for classification of the molar and the premolar teeth.…”

Section: Introductionmentioning

confidence: 99%

Büyükten Küçüğe Oto-kodlayıcılar ile dişlerin konumlandırılması*

Oktay

2018

Bilişim Teknolojileri Dergisi

View full text Add to dashboard Cite

Localization of teeth is a prerequisite task for most of the computerized methods for dental images such as medical diagnosis and human identification. Classical deep learning architectures like convolutional neural networks and auto-encoders seem to work well for tooth detection, however, it is non-trivial because of the large dental image size. In this study, a coarse-to-fine stacked auto-encoder architecture is presented for detection of teeth in dental panoramic images. The proposed architecture involves cascaded stacked auto-encoders where sizes of the input patches are increased with the successive steps. Only the detected candidate tooth patches are fed into the successive layers, thus the irrelevant patches are eliminated. The proposed architecture decreases the cost of detection process while providing precise localization. The method is tested and validated on a dataset containing 210 dental panoramic images and the tooth detection accuracy of the system is 91%.

show abstract

Extraction of Teeth Shapes from Orthopantomograms for Forensic Human Identification

Cited by 12 publications

References 8 publications

Automatic Tooth Identification in Dental Panoramic Images with Atlas-based Models

Automatic Tooth Identification in Dental Panoramic Images with Atlas-based Models

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

Büyükten Küçüğe Oto-kodlayıcılar ile dişlerin konumlandırılması*

Contact Info

Product

Resources

About