Deep convolutional neural network designed for age assessment based on orthopantomography data

Seyed M.M. Kahaki, Md. Jan Nordin, Nazatul S. Ahmad, Mahir Arzoky, Waidah Ismail

Research output: Contribution to journalArticle

Abstract

In this paper, we proposed an age assessment method evaluated on Malaysian children aged between 1 and 17. The approach is based on global fuzzy segmentation, local feature extraction using a projection-based feature transform and a designed deep convolutional neural networks (DCNNs) model. In the first step, a global labelling process was achieved based on fuzzy segmentation, and then, the first-to-third molar teeth were segmented. The deformation invariant features were next extracted based on an intensity projection technique. This technique provided high-order features which were invariant to rotation and partial deformation changes. Finally, the designed DCNN model extracts a large set of features in the hierarchical layers which provided scale, rotation and deformation invariance. The method using this approach was evaluated using a comprehensive and labelled orthopantomographs of 456 patients, which were captured in the Department of Dentistry and Research at Universiti Sains Islam Malaysia. The results from the analysis have suggested that the method can classify the images with high performance, which enabled automated age estimation with high accuracy.

Original languageEnglish
JournalNeural Computing and Applications
DOIs
Publication statusAccepted/In press - 1 Jan 2019

Fingerprint

Neural networks
Dentistry
Invariance
Labeling
Feature extraction

Keywords

  • Age assessment
  • Deep learning
  • Image processing
  • Orthopantomography data

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Deep convolutional neural network designed for age assessment based on orthopantomography data. / Kahaki, Seyed M.M.; Nordin, Md. Jan; Ahmad, Nazatul S.; Arzoky, Mahir; Ismail, Waidah.

In: Neural Computing and Applications, 01.01.2019.

Research output: Contribution to journalArticle

@article{dbbfde46bc2f4425a2a086060407741b,
title = "Deep convolutional neural network designed for age assessment based on orthopantomography data",
abstract = "In this paper, we proposed an age assessment method evaluated on Malaysian children aged between 1 and 17. The approach is based on global fuzzy segmentation, local feature extraction using a projection-based feature transform and a designed deep convolutional neural networks (DCNNs) model. In the first step, a global labelling process was achieved based on fuzzy segmentation, and then, the first-to-third molar teeth were segmented. The deformation invariant features were next extracted based on an intensity projection technique. This technique provided high-order features which were invariant to rotation and partial deformation changes. Finally, the designed DCNN model extracts a large set of features in the hierarchical layers which provided scale, rotation and deformation invariance. The method using this approach was evaluated using a comprehensive and labelled orthopantomographs of 456 patients, which were captured in the Department of Dentistry and Research at Universiti Sains Islam Malaysia. The results from the analysis have suggested that the method can classify the images with high performance, which enabled automated age estimation with high accuracy.",
keywords = "Age assessment, Deep learning, Image processing, Orthopantomography data",
author = "Kahaki, {Seyed M.M.} and Nordin, {Md. Jan} and Ahmad, {Nazatul S.} and Mahir Arzoky and Waidah Ismail",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/s00521-019-04449-6",
language = "English",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer London",

}

TY - JOUR

T1 - Deep convolutional neural network designed for age assessment based on orthopantomography data

AU - Kahaki, Seyed M.M.

AU - Nordin, Md. Jan

AU - Ahmad, Nazatul S.

AU - Arzoky, Mahir

AU - Ismail, Waidah

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In this paper, we proposed an age assessment method evaluated on Malaysian children aged between 1 and 17. The approach is based on global fuzzy segmentation, local feature extraction using a projection-based feature transform and a designed deep convolutional neural networks (DCNNs) model. In the first step, a global labelling process was achieved based on fuzzy segmentation, and then, the first-to-third molar teeth were segmented. The deformation invariant features were next extracted based on an intensity projection technique. This technique provided high-order features which were invariant to rotation and partial deformation changes. Finally, the designed DCNN model extracts a large set of features in the hierarchical layers which provided scale, rotation and deformation invariance. The method using this approach was evaluated using a comprehensive and labelled orthopantomographs of 456 patients, which were captured in the Department of Dentistry and Research at Universiti Sains Islam Malaysia. The results from the analysis have suggested that the method can classify the images with high performance, which enabled automated age estimation with high accuracy.

AB - In this paper, we proposed an age assessment method evaluated on Malaysian children aged between 1 and 17. The approach is based on global fuzzy segmentation, local feature extraction using a projection-based feature transform and a designed deep convolutional neural networks (DCNNs) model. In the first step, a global labelling process was achieved based on fuzzy segmentation, and then, the first-to-third molar teeth were segmented. The deformation invariant features were next extracted based on an intensity projection technique. This technique provided high-order features which were invariant to rotation and partial deformation changes. Finally, the designed DCNN model extracts a large set of features in the hierarchical layers which provided scale, rotation and deformation invariance. The method using this approach was evaluated using a comprehensive and labelled orthopantomographs of 456 patients, which were captured in the Department of Dentistry and Research at Universiti Sains Islam Malaysia. The results from the analysis have suggested that the method can classify the images with high performance, which enabled automated age estimation with high accuracy.

KW - Age assessment

KW - Deep learning

KW - Image processing

KW - Orthopantomography data

UR - http://www.scopus.com/inward/record.url?scp=85072036337&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072036337&partnerID=8YFLogxK

U2 - 10.1007/s00521-019-04449-6

DO - 10.1007/s00521-019-04449-6

M3 - Article

AN - SCOPUS:85072036337

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

ER -