Open Access

ARTICLE

Artificially Generated Facial Images for Gender Classification Using Deep Learning

Valliappan Raman¹, Khaled ELKarazle^2,*, Patrick Then²

1 Coimbatore Institute of Technology, Coimbatore, 641014, India
2 Swinburne University of Technology, Kuching, 95530, Malaysia

* Corresponding Author: Khaled ELKarazle. Email:

Computer Systems Science and Engineering 2023, 44(2), 1341-1355. https://doi.org/10.32604/csse.2023.026674

Received 01 January 2022; Accepted 22 February 2022; Issue published 15 June 2022

Abstract

Given the current expansion of the computer vision field, several applications that rely on extracting biometric information like facial gender for access control, security or marketing purposes are becoming more common. A typical gender classifier requires many training samples to learn as many distinguishable features as possible. However, collecting facial images from individuals is usually a sensitive task, and it might violate either an individual's privacy or a specific data privacy law. In order to bridge the gap between privacy and the need for many facial images for deep learning training, an artificially generated dataset of facial images is proposed. We acquire a pre-trained Style-Generative Adversarial Networks (StyleGAN) generator and use it to create a dataset of facial images. We label the images according to the observed gender using a set of criteria that differentiate the facial features of males and females apart. We use this manually-labelled dataset to train three facial gender classifiers, a custom-designed network, and two pre-trained networks based on the Visual Geometry Group designs (VGG16) and (VGG19). We cross-validate these three classifiers on two separate datasets containing labelled images of actual subjects. For testing, we use the UTKFace and the Kaggle gender dataset. Our experimental results suggest that using a set of artificial images for training produces a comparable performance with accuracies similar to existing state-of-the-art methods, which uses actual images of individuals. The average classification accuracy of each classifier is between 94% and 95%, which is similar to existing proposed methods.

---

Keywords

---