Multi-level Multi-scale Deep Feature Encoding for Chronological Age Estimation from OPG Images
Age estimation is a complex task in forensic dentistry especially if the bodies have started to decompose. However, when the task involves Manually examining, the accuracy can decrease due varying experience of the experts, the results of different experts may also vary. To improve speed and accurac...
Saved in:
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
University of Portsmouth
2023
|
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.uniten.dspace-26645 |
|---|---|
| record_format |
dspace |
| spelling |
my.uniten.dspace-266452023-05-29T17:36:01Z Multi-level Multi-scale Deep Feature Encoding for Chronological Age Estimation from OPG Images Alkaabi S. Yussof S. 57212311690 16023225600 Age estimation is a complex task in forensic dentistry especially if the bodies have started to decompose. However, when the task involves Manually examining, the accuracy can decrease due varying experience of the experts, the results of different experts may also vary. To improve speed and accuracy of the age estimation process using forensic dentistry, researchers have proposed Convolutional Neural Network for Dental Age and Sex Network estimation (DASNET). However, pooling and scalar outputs of CNNs could not allow to get the equivariance due to the dental extraction complexity from panoramic images including jaws, teeth, lesions and carries. So, a deep auto-encoder decoder architecture has been developed by the authors, which estimates the age based on semantic and structural feature representation. The age ranges are chosen based on the structural variation of the jaw in these particular age ranges as compared to each other. The authors have proposed a Convolution Long Short Term Memory (ConvLSTM) to capture the correlation of features and generates high level representation of features. For the representation of the generated features, authors have utilized �Atrous pyramid convolution� to produce a multiscale representation. The authors have proposed a combination of multi-scale and multi-level architecture for age estimation. First comes the first sub-part of the model that is the multi-level architecture, it is used for the extraction of hidden features. After that, the output is fed to second subpart which is the multi-scale architecture that enriches the model representation capability in encoding structural and shape characteristics. The propose techniques successfully reduces mean error to 0.75 years, as opposed to 0.93 years of the DASNET. � 2022 Journal of Image and Graphics. Final 2023-05-29T09:36:01Z 2023-05-29T09:36:01Z 2022 Article 10.18178/joig.10.4.151-157 2-s2.0-85140446367 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85140446367&doi=10.18178%2fjoig.10.4.151-157&partnerID=40&md5=a89ebf785238ca3766aaa044d189563f https://irepository.uniten.edu.my/handle/123456789/26645 10 4 151 157 All Open Access, Hybrid Gold University of Portsmouth Scopus |
| institution |
Universiti Tenaga Nasional |
| building |
UNITEN Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Tenaga Nasional |
| content_source |
UNITEN Institutional Repository |
| url_provider |
http://dspace.uniten.edu.my/ |
| description |
Age estimation is a complex task in forensic dentistry especially if the bodies have started to decompose. However, when the task involves Manually examining, the accuracy can decrease due varying experience of the experts, the results of different experts may also vary. To improve speed and accuracy of the age estimation process using forensic dentistry, researchers have proposed Convolutional Neural Network for Dental Age and Sex Network estimation (DASNET). However, pooling and scalar outputs of CNNs could not allow to get the equivariance due to the dental extraction complexity from panoramic images including jaws, teeth, lesions and carries. So, a deep auto-encoder decoder architecture has been developed by the authors, which estimates the age based on semantic and structural feature representation. The age ranges are chosen based on the structural variation of the jaw in these particular age ranges as compared to each other. The authors have proposed a Convolution Long Short Term Memory (ConvLSTM) to capture the correlation of features and generates high level representation of features. For the representation of the generated features, authors have utilized �Atrous pyramid convolution� to produce a multiscale representation. The authors have proposed a combination of multi-scale and multi-level architecture for age estimation. First comes the first sub-part of the model that is the multi-level architecture, it is used for the extraction of hidden features. After that, the output is fed to second subpart which is the multi-scale architecture that enriches the model representation capability in encoding structural and shape characteristics. The propose techniques successfully reduces mean error to 0.75 years, as opposed to 0.93 years of the DASNET. � 2022 Journal of Image and Graphics. |
| author2 |
57212311690 |
| author_facet |
57212311690 Alkaabi S. Yussof S. |
| format |
Article |
| author |
Alkaabi S. Yussof S. |
| spellingShingle |
Alkaabi S. Yussof S. Multi-level Multi-scale Deep Feature Encoding for Chronological Age Estimation from OPG Images |
| author_sort |
Alkaabi S. |
| title |
Multi-level Multi-scale Deep Feature Encoding for Chronological Age Estimation from OPG Images |
| title_short |
Multi-level Multi-scale Deep Feature Encoding for Chronological Age Estimation from OPG Images |
| title_full |
Multi-level Multi-scale Deep Feature Encoding for Chronological Age Estimation from OPG Images |
| title_fullStr |
Multi-level Multi-scale Deep Feature Encoding for Chronological Age Estimation from OPG Images |
| title_full_unstemmed |
Multi-level Multi-scale Deep Feature Encoding for Chronological Age Estimation from OPG Images |
| title_sort |
multi-level multi-scale deep feature encoding for chronological age estimation from opg images |
| publisher |
University of Portsmouth |
| publishDate |
2023 |
| _version_ |
1806425528830263296 |
| score |
13.222552 |