A fine-grained network for human identification using panoramic dental images
Summary: When accidents occur, panoramic dental images play a significant role in identifying unknown bodies. In recent years, deep neural networks have been applied to address this task. However, while tooth contours are significant in classical methods, few studies using deep learning methods devi...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-05-01
|
| Series: | Patterns |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666389922000708 |
| _version_ | 1818474871957487616 |
|---|---|
| author | Hu Chen Che Sun Peixi Liao Yancun Lai Fei Fan Yi Lin Zhenhua Deng Yi Zhang |
| author_facet | Hu Chen Che Sun Peixi Liao Yancun Lai Fei Fan Yi Lin Zhenhua Deng Yi Zhang |
| author_sort | Hu Chen |
| collection | DOAJ |
| description | Summary: When accidents occur, panoramic dental images play a significant role in identifying unknown bodies. In recent years, deep neural networks have been applied to address this task. However, while tooth contours are significant in classical methods, few studies using deep learning methods devise an architecture specifically to introduce tooth contours into their models. Since fine-grained image identification aims to distinguish subordinate categories by specific parts, we devise a fine-grained human identification model that leverages the distribution of tooth masks to distinguish different individuals with local and subtle differences in their teeth. First, a bilateral branched architecture is designed, of which one branch was designed as the image feature extractor, while the other was the mask feature extractor. In this step, the mask feature interacts with the extracted image feature to perform elementwise reweighting. Additionally, an improved attention mechanism was used to make our model concentrate more on informative positions. Furthermore, we improved the ArcFace loss by adding a learnable parameter to increase the loss of those hard samples, thereby exploiting the potential of our loss function. Our model was tested on a large dataset consisting of 23,715 panoramic X-ray dental images with tooth masks from 10,113 patients, achieving an average rank-1 accuracy of 88.62% and rank-10 accuracy of 96.16%. The bigger picture: DNA, fingerprints, faces, etc. have been used in human identification, but they are susceptible to decay when people die. Teeth do not decay, so experts use teeth as an effective feature in individual identification. In earlier times, experts did the comparation manually. Our model contains a branch devised specially to extract tooth contour features, which have proved to be meaningful in previous methods. With other improvements added, our model is able to identify the target person in 1,000 X-ray dental images with an accuracy of 88.62. There also exist limitations. The proposed model rests on masks, so in subsequent studies, we will perform unsupervised methods on teeth or other structures.Compared with DNA, panoramic dental X-ray images are easier to access, so our model provides a feasible approach for identifying unknown bodies if they took panoramic dental X-ray images when alive, even if these bodies are ossified. |
| first_indexed | 2024-04-14T04:42:14Z |
| format | Article |
| id | doaj.art-c991d4471ebd42429ffc0b3257ce3c7a |
| institution | Directory Open Access Journal |
| issn | 2666-3899 |
| language | English |
| last_indexed | 2024-04-14T04:42:14Z |
| publishDate | 2022-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Patterns |
| spelling | doaj.art-c991d4471ebd42429ffc0b3257ce3c7a2022-12-22T02:11:37ZengElsevierPatterns2666-38992022-05-0135100485A fine-grained network for human identification using panoramic dental imagesHu Chen0Che Sun1Peixi Liao2Yancun Lai3Fei Fan4Yi Lin5Zhenhua Deng6Yi Zhang7College of Computer Science, Sichuan University, Chengdu, Sichuan, ChinaCollege of Computer Science, Sichuan University, Chengdu, Sichuan, ChinaDepartment of Scientific Research and Education, The Sixth People’s Hospital of Chengdu, Chengdu, Sichuan, ChinaCollege of Computer Science, Sichuan University, Chengdu, Sichuan, ChinaWest China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, Sichuan, China; Corresponding authorCollege of Computer Science, Sichuan University, Chengdu, Sichuan, ChinaWest China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, Sichuan, ChinaCollege of Computer Science, Sichuan University, Chengdu, Sichuan, China; Corresponding authorSummary: When accidents occur, panoramic dental images play a significant role in identifying unknown bodies. In recent years, deep neural networks have been applied to address this task. However, while tooth contours are significant in classical methods, few studies using deep learning methods devise an architecture specifically to introduce tooth contours into their models. Since fine-grained image identification aims to distinguish subordinate categories by specific parts, we devise a fine-grained human identification model that leverages the distribution of tooth masks to distinguish different individuals with local and subtle differences in their teeth. First, a bilateral branched architecture is designed, of which one branch was designed as the image feature extractor, while the other was the mask feature extractor. In this step, the mask feature interacts with the extracted image feature to perform elementwise reweighting. Additionally, an improved attention mechanism was used to make our model concentrate more on informative positions. Furthermore, we improved the ArcFace loss by adding a learnable parameter to increase the loss of those hard samples, thereby exploiting the potential of our loss function. Our model was tested on a large dataset consisting of 23,715 panoramic X-ray dental images with tooth masks from 10,113 patients, achieving an average rank-1 accuracy of 88.62% and rank-10 accuracy of 96.16%. The bigger picture: DNA, fingerprints, faces, etc. have been used in human identification, but they are susceptible to decay when people die. Teeth do not decay, so experts use teeth as an effective feature in individual identification. In earlier times, experts did the comparation manually. Our model contains a branch devised specially to extract tooth contour features, which have proved to be meaningful in previous methods. With other improvements added, our model is able to identify the target person in 1,000 X-ray dental images with an accuracy of 88.62. There also exist limitations. The proposed model rests on masks, so in subsequent studies, we will perform unsupervised methods on teeth or other structures.Compared with DNA, panoramic dental X-ray images are easier to access, so our model provides a feasible approach for identifying unknown bodies if they took panoramic dental X-ray images when alive, even if these bodies are ossified.http://www.sciencedirect.com/science/article/pii/S2666389922000708DSML 2: Proof-of-concept: Data science output has been formulated, implemented, and tested for one domain/problem |
| spellingShingle | Hu Chen Che Sun Peixi Liao Yancun Lai Fei Fan Yi Lin Zhenhua Deng Yi Zhang A fine-grained network for human identification using panoramic dental images Patterns DSML 2: Proof-of-concept: Data science output has been formulated, implemented, and tested for one domain/problem |
| title | A fine-grained network for human identification using panoramic dental images |
| title_full | A fine-grained network for human identification using panoramic dental images |
| title_fullStr | A fine-grained network for human identification using panoramic dental images |
| title_full_unstemmed | A fine-grained network for human identification using panoramic dental images |
| title_short | A fine-grained network for human identification using panoramic dental images |
| title_sort | fine grained network for human identification using panoramic dental images |
| topic | DSML 2: Proof-of-concept: Data science output has been formulated, implemented, and tested for one domain/problem |
| url | http://www.sciencedirect.com/science/article/pii/S2666389922000708 |
| work_keys_str_mv | AT huchen afinegrainednetworkforhumanidentificationusingpanoramicdentalimages AT chesun afinegrainednetworkforhumanidentificationusingpanoramicdentalimages AT peixiliao afinegrainednetworkforhumanidentificationusingpanoramicdentalimages AT yancunlai afinegrainednetworkforhumanidentificationusingpanoramicdentalimages AT feifan afinegrainednetworkforhumanidentificationusingpanoramicdentalimages AT yilin afinegrainednetworkforhumanidentificationusingpanoramicdentalimages AT zhenhuadeng afinegrainednetworkforhumanidentificationusingpanoramicdentalimages AT yizhang afinegrainednetworkforhumanidentificationusingpanoramicdentalimages AT huchen finegrainednetworkforhumanidentificationusingpanoramicdentalimages AT chesun finegrainednetworkforhumanidentificationusingpanoramicdentalimages AT peixiliao finegrainednetworkforhumanidentificationusingpanoramicdentalimages AT yancunlai finegrainednetworkforhumanidentificationusingpanoramicdentalimages AT feifan finegrainednetworkforhumanidentificationusingpanoramicdentalimages AT yilin finegrainednetworkforhumanidentificationusingpanoramicdentalimages AT zhenhuadeng finegrainednetworkforhumanidentificationusingpanoramicdentalimages AT yizhang finegrainednetworkforhumanidentificationusingpanoramicdentalimages |