Recent Generative Adversarial Approach in Face Aging and Dataset Review
Many studies have been conducted in the field of face aging, from approaches that use pure image-processing algorithms, to those that use generative adversarial networks. In this study, we review a classic approach that uses a generative adversarial network. The structure, formulation, learning algo...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2022-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9729822/ |
_version_ | 1811342211116171264 |
---|---|
author | Hady Pranoto Yaya Heryadi Harco Leslie Hendric Spits Warnars Widodo Budiharto |
author_facet | Hady Pranoto Yaya Heryadi Harco Leslie Hendric Spits Warnars Widodo Budiharto |
author_sort | Hady Pranoto |
collection | DOAJ |
description | Many studies have been conducted in the field of face aging, from approaches that use pure image-processing algorithms, to those that use generative adversarial networks. In this study, we review a classic approach that uses a generative adversarial network. The structure, formulation, learning algorithm, challenges, advantages, and disadvantages of the algorithms contained in each proposed algorithm are discussed systematically. Generative Adversarial Networks are an approach that obtains the status of the art in the field of face aging by adding an aging module, paying special attention to the face part, and using an identity-preserving module to preserve identity. In this paper, we also discuss the database used for facial aging, along with its characteristics. The dataset used in the face aging process must have the following criteria: (1) a sufficiently large age group in the dataset, each age group must have a small range, (2) a balanced distribution of each age group, and (3) has enough number of face images. |
first_indexed | 2024-04-13T19:07:34Z |
format | Article |
id | doaj.art-e18d4696f5174b40b89e8754c3a424be |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-13T19:07:34Z |
publishDate | 2022-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-e18d4696f5174b40b89e8754c3a424be2022-12-22T02:33:57ZengIEEEIEEE Access2169-35362022-01-0110286932871610.1109/ACCESS.2022.31576179729822Recent Generative Adversarial Approach in Face Aging and Dataset ReviewHady Pranoto0https://orcid.org/0000-0002-3685-0934Yaya Heryadi1Harco Leslie Hendric Spits Warnars2https://orcid.org/0000-0002-5942-417XWidodo Budiharto3https://orcid.org/0000-0003-2681-0901Computer Science Department, BINUS Graduate Program-Doctor of Computer Science, Bina Nusantara University, Jakarta, IndonesiaComputer Science Department, BINUS Graduate Program-Doctor of Computer Science, Bina Nusantara University, Jakarta, IndonesiaComputer Science Department, BINUS Graduate Program-Doctor of Computer Science, Bina Nusantara University, Jakarta, IndonesiaComputer Science Department, School of Computer Science, Bina Nusantara University, Jakarta, IndonesiaMany studies have been conducted in the field of face aging, from approaches that use pure image-processing algorithms, to those that use generative adversarial networks. In this study, we review a classic approach that uses a generative adversarial network. The structure, formulation, learning algorithm, challenges, advantages, and disadvantages of the algorithms contained in each proposed algorithm are discussed systematically. Generative Adversarial Networks are an approach that obtains the status of the art in the field of face aging by adding an aging module, paying special attention to the face part, and using an identity-preserving module to preserve identity. In this paper, we also discuss the database used for facial aging, along with its characteristics. The dataset used in the face aging process must have the following criteria: (1) a sufficiently large age group in the dataset, each age group must have a small range, (2) a balanced distribution of each age group, and (3) has enough number of face images.https://ieeexplore.ieee.org/document/9729822/Face recognitionimage generationimage databaseface aging datasetdeep generative approachgenerative adversarial network |
spellingShingle | Hady Pranoto Yaya Heryadi Harco Leslie Hendric Spits Warnars Widodo Budiharto Recent Generative Adversarial Approach in Face Aging and Dataset Review IEEE Access Face recognition image generation image database face aging dataset deep generative approach generative adversarial network |
title | Recent Generative Adversarial Approach in Face Aging and Dataset Review |
title_full | Recent Generative Adversarial Approach in Face Aging and Dataset Review |
title_fullStr | Recent Generative Adversarial Approach in Face Aging and Dataset Review |
title_full_unstemmed | Recent Generative Adversarial Approach in Face Aging and Dataset Review |
title_short | Recent Generative Adversarial Approach in Face Aging and Dataset Review |
title_sort | recent generative adversarial approach in face aging and dataset review |
topic | Face recognition image generation image database face aging dataset deep generative approach generative adversarial network |
url | https://ieeexplore.ieee.org/document/9729822/ |
work_keys_str_mv | AT hadypranoto recentgenerativeadversarialapproachinfaceaginganddatasetreview AT yayaheryadi recentgenerativeadversarialapproachinfaceaginganddatasetreview AT harcolesliehendricspitswarnars recentgenerativeadversarialapproachinfaceaginganddatasetreview AT widodobudiharto recentgenerativeadversarialapproachinfaceaginganddatasetreview |