Development Study of Deep Learning Facial Age Estimation
Human age estimation is one of the most challenging problem because it can be used in many applications relating to age such as age-specific movies, age-specific computer applications or website, etc. This paper will contribute to give brief information about development of age estimation researches...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
Universitas Sanata Dharma
2019-06-01
|
Series: | International Journal of Applied Sciences and Smart Technologies |
Online Access: | https://e-journal.usd.ac.id/index.php/IJASST/article/view/1899 |
_version_ | 1811288509481222144 |
---|---|
author | Puspaningtyas Sanjoyo Adi |
author_facet | Puspaningtyas Sanjoyo Adi |
author_sort | Puspaningtyas Sanjoyo Adi |
collection | DOAJ |
description | Human age estimation is one of the most challenging problem because it can be used in many applications relating to age such as age-specific movies, age-specific computer applications or website, etc. This paper will contribute to give brief information about development of age estimation researches using deep learning. We explore three recent journal papers that give significant contribution in age estimation using deep learning. From these papers, they selected classification methods and there is gradual improvement in result and also in selected loss function. The best result gives MAE (mean average error) 2.8 years and VGG-16 is the most selected CNN architecture. |
first_indexed | 2024-04-13T03:38:17Z |
format | Article |
id | doaj.art-a014227c707d4f239eccb58a889a6981 |
institution | Directory Open Access Journal |
issn | 2655-8564 |
language | English |
last_indexed | 2024-04-13T03:38:17Z |
publishDate | 2019-06-01 |
publisher | Universitas Sanata Dharma |
record_format | Article |
series | International Journal of Applied Sciences and Smart Technologies |
spelling | doaj.art-a014227c707d4f239eccb58a889a69812022-12-22T03:04:16ZengUniversitas Sanata DharmaInternational Journal of Applied Sciences and Smart Technologies2655-85642019-06-0111455010.24071/ijasst.v1i1.18991406Development Study of Deep Learning Facial Age EstimationPuspaningtyas Sanjoyo Adi0Universitas Sanata DharmaHuman age estimation is one of the most challenging problem because it can be used in many applications relating to age such as age-specific movies, age-specific computer applications or website, etc. This paper will contribute to give brief information about development of age estimation researches using deep learning. We explore three recent journal papers that give significant contribution in age estimation using deep learning. From these papers, they selected classification methods and there is gradual improvement in result and also in selected loss function. The best result gives MAE (mean average error) 2.8 years and VGG-16 is the most selected CNN architecture.https://e-journal.usd.ac.id/index.php/IJASST/article/view/1899 |
spellingShingle | Puspaningtyas Sanjoyo Adi Development Study of Deep Learning Facial Age Estimation International Journal of Applied Sciences and Smart Technologies |
title | Development Study of Deep Learning Facial Age Estimation |
title_full | Development Study of Deep Learning Facial Age Estimation |
title_fullStr | Development Study of Deep Learning Facial Age Estimation |
title_full_unstemmed | Development Study of Deep Learning Facial Age Estimation |
title_short | Development Study of Deep Learning Facial Age Estimation |
title_sort | development study of deep learning facial age estimation |
url | https://e-journal.usd.ac.id/index.php/IJASST/article/view/1899 |
work_keys_str_mv | AT puspaningtyassanjoyoadi developmentstudyofdeeplearningfacialageestimation |