Department of Electrical and Electronic Engineering Science, University of Johannesburg, Johannesburg 2006, South Africa
Email: ysun@uj.ac.za (Y. S.)
*Corresponding author
Manuscript received September 13, 2023; revised May 29, 2024; accepted July 4, 2024; published 18 November 2024
Abstract—Age estimation of an individual facial image has become a fascinating research topic due to its wide range of applications in real-world scenarios. In literature, significant research has been done using various techniques and approaches; these studies gave a good outcome, making this area of research a state-of-the-art area for research and giving space for more enhanced accuracy. This study aims to improve age estimation using facial biometric features by applying deep learning and transfer learning techniques. By doing this, the research aims to solve the problem of inaccurate age estimation based on facial images. This study proposed using an improved Genetic Algorithm coupled with a Convolutional Neural network (CNN) model (EfficientNet-B0) to estimate age on the Adience benchmark dataset. This study applied a Genetic algorithm for the selection of hyperparameters to help achieve an optimal result. The EfficientNet-B0 + Genetic Algorithm (GA) model's estimation accuracy yielded a good accuracy of 86.5%, which shows an improvement compared to work in the literature that used other models.
Keywords—age estimation, feature extraction, deep learning, machine learning, neural networks
[PDF]
Cite: Idowu T. Aruleba and Yanxia Sun, "Deep Learning and Genetic Algorithms Approach for Age Estimation Based on Facial Images," International Journal of Computer Theory and Engineering, vol. 16, no. 4, pp. 127-133, 2024.
Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
