Cargando…

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

Detalles Bibliográficos
Autores principales: Hung, Shih-Kai, Gan, John Q.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8627232/
https://www.ncbi.nlm.nih.gov/pubmed/34901424
http://dx.doi.org/10.7717/peerj-cs.760
_version_ 1784606812309291008
author Hung, Shih-Kai
Gan, John Q.
author_facet Hung, Shih-Kai
Gan, John Q.
author_sort Hung, Shih-Kai
collection PubMed
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 Online
Article
Text
id pubmed-8627232
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-86272322021-12-10 Small facial image dataset augmentation using conditional GANs based on incomplete edge feature input Hung, Shih-Kai Gan, John Q. PeerJ Comput Sci Artificial Intelligence 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. PeerJ Inc. 2021-11-17 /pmc/articles/PMC8627232/ /pubmed/34901424 http://dx.doi.org/10.7717/peerj-cs.760 Text en ©2021 Hung and Gan https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited.
spellingShingle Artificial Intelligence
Hung, Shih-Kai
Gan, John Q.
Small facial image dataset augmentation using conditional GANs based on incomplete edge feature input
title 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_short 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
topic Artificial Intelligence
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8627232/
https://www.ncbi.nlm.nih.gov/pubmed/34901424
http://dx.doi.org/10.7717/peerj-cs.760
work_keys_str_mv AT hungshihkai smallfacialimagedatasetaugmentationusingconditionalgansbasedonincompleteedgefeatureinput
AT ganjohnq smallfacialimagedatasetaugmentationusingconditionalgansbasedonincompleteedgefeatureinput