Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Oct 10, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

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

Shih-Kai Hung¹, John Q Gan¹

¹School of Computer Science and Electronic Engineering, University of Essex, Colchester, United Kingdom.

Peerj. Computer Science

|December 13, 2021

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

3D-Printed Bolus-Assisted Radiotherapy for Converting Unresectable Breast Cancer with a Breast Prosthesis into a Resectable Condition: A Case Report.

Current oncology (Toronto, Ont.)·2026

Same author

Modulated electro-hyperthermia enhances tumor cell susceptibility to γδ T cell-mediated cytotoxicity and tumor infiltration in NOD/SCID xenograft models.

International journal of hyperthermia : the official journal of European Society for Hyperthermic Oncology, North American Hyperthermia Group·2026

Same author

Methylated PIH1D1 as a Heart-Specific Biomarker for Anthracycline-Induced Cardiac Remodeling in Breast Cancer Patients.

JACC. Basic to translational science·2026

Same author

Cogformer: A Unified Multi-Scale Brain Representation for Visual Decoding and Reconstruction From fMRI.

IEEE transactions on medical imaging·2026

Same author

Advancing skin cancer detection through deep learning and fusion of patient metadata and skin lesion images.

Scientific reports·2026

Same author

Comparing irradiated clinical outcomes between modified radical mastectomy and breast-conserving surgery in patients with pathologic stage III breast cancer: A national population-based match cohort study.

Surgery·2025

Same journal

DARUMA: a gateway to fast and easy prediction of intrinsically disordered regions.

PeerJ. Computer science·2026

Same journal

Alzheimer's disease detection using a quantum deep neural network with Haralick feature extraction and simulated annealing optimization.

PeerJ. Computer science·2026

Same journal

Network anomaly detection using Deep Autoencoder and parallel Artificial Bee Colony algorithm-trained neural network.

PeerJ. Computer science·2026

Same journal

An anomaly detection model for multivariate time series with anomaly perception.

PeerJ. Computer science·2026

Same journal

Retraction: A wormhole attack detection method for tactical wireless sensor networks.

PeerJ. Computer science·2026

Same journal

Evaluation of mental disorder with prioritization of its type by utilizing the bipolar complex fuzzy decision-making approach based on Schweizer-Sklar prioritized aggregation operators.

PeerJ. Computer science·2026

See all related articles

This study introduces a new conditional generative adversarial network (GAN) framework for facial image augmentation. The method effectively generates diverse, high-quality images from small datasets using incomplete edge features, outperforming existing techniques.

Area of Science:

Computer Vision
Artificial Intelligence
Machine Learning

Background:

Image data collection and labeling are expensive and time-consuming.
Deep learning models, particularly Convolutional Neural Networks (CNNs), require large datasets for optimal performance.
Generating diverse and controllable images for data augmentation using conditional Generative Adversarial Networks (GANs) from limited data is a significant challenge.

Purpose of the Study:

To propose a novel conditional GAN framework for facial image augmentation using very small training datasets.
To leverage incomplete or modified edge features as conditional input for generating diverse images.
To enhance image quality and prevent overfitting in data augmentation scenarios.

Main Methods:

Developed a conditional GAN framework specifically for facial image augmentation.

Keywords:

Deep convolutional neural networks Generative adversarial networks Image data augmentation Overfitting Small training data

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Oct 10, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Utilized pre-processed, incomplete edge features (e.g., simplified lines, discontinuous shapes) as conditional inputs.

Introduced a new domain/space for refining intermediate images to mitigate overfitting and improve distortion tolerance.

Main Results:

The proposed method successfully generates high-quality facial images with good diversity, even with sparse edges and minimal training samples.
Achieved superior performance compared to state-of-the-art edge-to-image translation methods when using small datasets.
Demonstrated significant improvements in synthesized image quality, validated by Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) scores.

Conclusions:

The conditional GAN framework effectively addresses the challenge of facial image augmentation with limited data.
The approach enhances image quality and diversity, making it suitable for dataset augmentation.
This method offers a robust solution for generating realistic facial images from incomplete edge information.