Automatic human identification from panoramic dental radiographs using the convolutional neural network. (September 2020)

• Record Type: Journal Article
• Authors: Fan, Fei; Ke, Wenchi; Wu, Wei; Tian, Xuemei; Lyu, Tu; Liu, Yuanyuan; Liao, Peixi; Dai, Xinhua; Chen, Hu; Deng, Zhenhua
• Is Part Of: Forensic science international. Volume 314(2020)
• Publication Date: 2020-09
• Subjects: Forensic odontology -- Human identification -- Panoramic dental radiographs -- Deep learning -- Convolutional neural network; Medical jurisprudence -- Periodicals; Chemistry, Forensic -- Periodicals; Forensic Medicine -- Periodicals; Médecine légale -- Périodiques; Chimie légale -- Périodiques; Gerechtelijke geneeskunde; Gerechtelijke chemie; Gerechtelijke psychiatrie; Chemistry, Forensic; Medical jurisprudence; Electronic journals; Periodicals; Electronic journals; 614.1
• DOI: 10.1016/j.forsciint.2020.110416
• Languages: English
• ISSNs: 0379-0738

Abstract

Highlights: We proposed an automatic human identification system from PDRs by using CNN. A total of 15, 868 PDRs from 6473 individuals are used to train and evaluate the CNN. The teeth, maxilla and mandible were all contributed to human identification. Rank-1 accuracy of 85.16% and Rank-5 accuracy of 97.74% for human identification. Human identification can be achieved from PDRs by CNN with high accuracy and speed. Abstract: Human identification is an important task in mass disaster and criminal investigations. Although several automatic dental identification systems have been proposed, accurate and fast identification from panoramic dental radiographs (PDRs) remains a challenging issue. In this study, an automatic human identification system (DENT-net) was developed using the customized convolutional neural network (CNN). The DENT-net was trained on 15, 369 PDRs from 6300 individuals. The PDRs were preprocessed by affine transformation and histogram equalization. The DENT-net took 128 × 128 × 7 square patches as input, including the whole PDR and six details extracted from the PDR. Using the DENT-net, the feature extraction took around 10 milliseconds per image and the running time for retrieval was 33.03 milliseconds in a 2000-individual database, promising an application on larger databases. The visualization of CNN showed that the teeth, maxilla, and mandible all contributed to human identification. The DENT-net achieved Rank-1 accuracy of 85.16% and Rank-5 accuracy of 97.74% for human identification. The present results demonstrated that human identification can be achieved from PDRs by CNN with high accuracy and speed. The present system can be used without any special equipment or knowledge to generate the candidate images. While the final decision should be made by human specialists in practice. It is expected to aid human identification in mass disaster and criminal investigation.