Human Age Estimation Using Deep Convolutional Neural Network based on Dental Images (Orthopantomogram)

Abstract

Age determination is the task of automatically distinguishing the age of an individual by using various kinds of inputs. Age estimation is the primary challenge in several fields such as legal requirements, immigrant identification, and clinical therapies. Of late, age estimation is done from orthopantomogram images with the help of machine learning approaches. Conventional approaches use convolutional neural networks for age. Performance comparisons between the human technique and automated methods done on a sample of orthopantomogram images are lacking in recent applications of deep learning for age estimation (OPGs). A convolutional neural network (CNN) with an end-to-end classification of age was developed. The technique is based on the third molar teeth. Our main aim is to incorporate CNN Classification models such as ResNet and Sequential to determine age classifications and hence our results surpassed 91% and 93% of accuracy levels in age classification using CNN models.

Keywords:

• Age estimation
• Chronological age
• Classification
• Convolution Neural network
• Dental age
• Orthopantomography

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

S. Sathyavathi

S Sathyavathi received her BTech degree in computer science and engineering from Sri Krishna College of Engineering and Technology, Coimbatore, India, in 2003, and MTech degree in computer science and engineering from the same college, in 2008. She is currently pursuing PhD at the Department of Information and Communication Engineering, Anna University, India. Her areas of interest are software engineering, data mining, deep learning, artificial intelligence, machine learning, and human-computer interaction.

K.R. Baskaran

K R Baskaran received the BE degree in computer science and engineering from Madurai-Kamaraj University, MS degree in software systems from Birla Institute of Technology and Science, Pilani, India, ME degree in computer science and engineering from Kumaraguru College of Technology and PhD from Anna University, Chennai, in 2015. His areas of interest are data analytics, machine learning, operating systems and compiler design. Email: [email protected]