Research Repository

Small facial image dataset augmentation using conditional GANs based on incomplete edge feature input

Hung, Shih-Kai and Gan, John Q (2021) 'Small facial image dataset augmentation using conditional GANs based on incomplete edge feature input.' PeerJ Computer Science, 7. e760-e760. ISSN 2376-5992

[img]
Preview
Text
peerj-cs-760.pdf - Published Version
Available under License Creative Commons Attribution.

Download (3MB) | Preview

Abstract

Image data collection and labelling is costly or difficult in many real applications. Generating diverse and controllable images using conditional generative adversarial networks (GANs) for data augmentation from a small dataset is promising but challenging as deep convolutional neural networks need a large training dataset to achieve reasonable performance in general. However, unlabeled and incomplete features (<jats:italic>e.g.,</jats:italic> unintegral edges, simplified lines, hand-drawn sketches, discontinuous geometry shapes, etc.) can be conveniently obtained through pre-processing the training images and can be used for image data augmentation. This paper proposes a conditional GAN framework for facial image augmentation using a very small training dataset and incomplete or modified edge features as conditional input for diversity. The proposed method defines a new domain or space for refining interim images to prevent overfitting caused by using a very small training dataset and enhance the tolerance of distortions caused by incomplete edge features, which effectively improves the quality of facial image augmentation with diversity. Experimental results have shown that the proposed method can generate high-quality images of good diversity when the GANs are trained using very sparse edges and a small number of training samples. Compared to the state-of-the-art edge-to-image translation methods that directly convert sparse edges to images, when using a small training dataset, the proposed conditional GAN framework can generate facial images with desirable diversity and acceptable distortions for dataset augmentation and significantly outperform the existing methods in terms of the quality of synthesised images, evaluated by Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) scores.

Item Type: Article
Uncontrolled Keywords: Generative adversarial networks; Deep convolutional neural networks; Image data augmentation; Small training data; Overfitting
Divisions: Faculty of Science and Health
Faculty of Science and Health > Computer Science and Electronic Engineering, School of
SWORD Depositor: Elements
Depositing User: Elements
Date Deposited: 20 Dec 2021 15:46
Last Modified: 15 Jan 2022 01:39
URI: http://repository.essex.ac.uk/id/eprint/31755

Actions (login required)

View Item View Item