Abstract
Human identification using tooth plays a crucial role in disaster victim identification. Traditional tooth recognition methods like iterative closest point (ICP) require laborious pairwise registration, so in this paper we focus on deep learning methods for human identification using tooth. We propose a complete workflow for tooth segmentation and recognition based on PointNet++ using the 3D intraoral scanning (IOS) model. Our method consists of two main components: an improved PointNet++ based tooth segmentation approach and a tooth recognition method that combines curvature feature extraction with improved PointNet++ using the segmented tooth part. To evaluate the identification method, we collect 240 IOS models, in which 208 models are used for training, and 32 models acquired for the second time are used for testing. The experimental results achieve a recognition accuracy of 96.88% on the test set, which demonstrates the potential of using the IOS model and deep learning methods for fully-automatedly human identification using tooth.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anslinger, K., Bayer, B.: Whose blood is it? Application of DEPArray technology for the identification of individuals who contributed blood to a mixed stain. Legal Med. 133(2), 419–426 (2019)
Lyu, T., Tian, X.: The necessity and possibility of dental identification in China. Forensic Med. 4, 321 (2019)
Reesu, G.V., Woodsend, B., Scheila, M., et al.: Automated Identification from Dental Data (AutoIDD): A New Development in Digital Forensics. Forensic Sci. Int. 309, 110218 (2020)
Abduo, J., Bennamoun, M.: Three-dimensional image registration as a tool for forensic odontology: a preliminary investigation. Am. J. Forensic Med. Pathol. 34(3), 260–266 (2013)
Qi, C.R., Su, H., Mo, K., et al.: PointNet: deep learning on point sets for 3D classification and segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 77–85. IEEE Press (2017)
Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Guyon, I., Von Luxburg, U., Bengio, S., et al., (Eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 5099–5108. Curran Associates, Red Hook (2017)
Lee, S.S., Choi, J.H., et al.: The diversity of dental patterns in the orthopanthomography and its significance in human identification. Forensic Sci. (Wiley-Blackwell) 49(4), 784–786 (2004)
Franco, A., Orestes, S.G.F., de Fátima Coimbra, E., et al.: Comparing dental identifier charting in cone beam computed tomography scans and panoramic radiographs using INTERPOL coding for human identification. Forensic Sci. Int., 1872–6283 (2020)
Fan, F., Ke, W.C., Wu, W., et al.: Automatic human identification from panoramic dental radiographs using the convolutional neural network. Forensic Sci. Int. 314, 110416 (2020)
Lai, Y.C., Fan, F., Wu, Q.S., et al.: LCANet: learnable connected attention network for human identification using dental images. IEEE Trans. Med. Imaging 40(3), 905–915 (2021)
Cheng, Y., Huang, Z., Quan, S., et al.: Sampling locally, hypothesis globally: accurate 3D point cloud registration with a RANSAC variant. Vis. Intell. 1, 20 (2023)
Gibelli, D., De Angelis, D., Riboli, F., Dolci, C., Cattaneo, C., Sforza, C.: Quantification of odontological differences of the upper first and second molar by 3D–3D superimposition: a novel method to assess anatomical matches. Forensic Sci. 15(4), 570–573 (2019)
Franco, A., Willems, G., Souza, P.H.C., Coucke, W., Thevissen, P.: Uniqueness of the anterior dentition three-dimensionally assessed for forensic bitemark analysis. Forensic Leg. Med. 46, 58–65 (2017)
Chong, G., Forgie, A.: A pilot study to analyze the uniqueness of anterior teeth using a novel three-dimensional approach. Forensic Identif. 67, 381–398 (2017)
Qnma, B., Llja, B., Yan, L.C., et al.: Three-dimensional superimposition of digital models for individual identification. Forensic Sci. Int. 318, 110597 (2020)
Yang, Y., Cui, Z., Xu, J., et al.: Continual learning with Bayesian model based on a fixed pre-trained feature extractor. Vis. Intell. 1, 5 (2023)
Yuan, L., Liu, X., Yu, J., Li, Y.: A full-set tooth segmentation model based on improved PointNet++. Vis. Intell. 1, 21 (2023)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, X., Yuan, L., Jiang, C., JiannanYu, Li, Y. (2023). Human Identification Using Tooth Based on PointNet++ . In: Jia, W., et al. Biometric Recognition. CCBR 2023. Lecture Notes in Computer Science, vol 14463. Springer, Singapore. https://doi.org/10.1007/978-981-99-8565-4_13
Download citation
DOI: https://doi.org/10.1007/978-981-99-8565-4_13
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8564-7
Online ISBN: 978-981-99-8565-4
eBook Packages: Computer ScienceComputer Science (R0)