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

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...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shih-Kai Hung, John Q. Gan
Formato:	article
Lenguaje:	EN
Publicado:	PeerJ Inc. 2021
Materias:	Generative adversarial networks Deep convolutional neural networks Image data augmentation Small training data Overfitting Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/569aead76726429dabfe1c8d961f130f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:569aead76726429dabfe1c8d961f130f
record_format	dspace
spelling	oai:doaj.org-article:569aead76726429dabfe1c8d961f130f2021-11-19T15:05:07ZSmall facial image dataset augmentation using conditional GANs based on incomplete edge feature input10.7717/peerj-cs.7602376-5992https://doaj.org/article/569aead76726429dabfe1c8d961f130f2021-11-01T00:00:00Zhttps://peerj.com/articles/cs-760.pdfhttps://peerj.com/articles/cs-760/https://doaj.org/toc/2376-5992Image 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 (e.g., 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.Shih-Kai HungJohn Q. GanPeerJ Inc.articleGenerative adversarial networksDeep convolutional neural networksImage data augmentationSmall training dataOverfittingElectronic computers. Computer scienceQA75.5-76.95ENPeerJ Computer Science, Vol 7, p e760 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Generative adversarial networks Deep convolutional neural networks Image data augmentation Small training data Overfitting Electronic computers. Computer science QA75.5-76.95
spellingShingle	Generative adversarial networks Deep convolutional neural networks Image data augmentation Small training data Overfitting Electronic computers. Computer science QA75.5-76.95 Shih-Kai Hung John Q. Gan Small facial image dataset augmentation using conditional GANs based on incomplete edge feature input
description	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 (e.g., 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.
format	article
author	Shih-Kai Hung John Q. Gan
author_facet	Shih-Kai Hung John Q. Gan
author_sort	Shih-Kai Hung
title	Small facial image dataset augmentation using conditional GANs based on incomplete edge feature input
title_short	Small facial image dataset augmentation using conditional GANs based on incomplete edge feature input
title_full	Small facial image dataset augmentation using conditional GANs based on incomplete edge feature input
title_fullStr	Small facial image dataset augmentation using conditional GANs based on incomplete edge feature input
title_full_unstemmed	Small facial image dataset augmentation using conditional GANs based on incomplete edge feature input
title_sort	small facial image dataset augmentation using conditional gans based on incomplete edge feature input
publisher	PeerJ Inc.
publishDate	2021
url	https://doaj.org/article/569aead76726429dabfe1c8d961f130f
work_keys_str_mv	AT shihkaihung smallfacialimagedatasetaugmentationusingconditionalgansbasedonincompleteedgefeatureinput AT johnqgan smallfacialimagedatasetaugmentationusingconditionalgansbasedonincompleteedgefeatureinput
_version_	1718420012896616448

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

Ejemplares similares