Facial Age Estimation Using Multi-Stage Deep Neural Networks

Over the last decade, the world has witnessed many breakthroughs in artificial intelligence, largely due to advances in deep learning technology. Notably, computer vision solutions have significantly contributed to these achievements. Human face analysis, a core area of computer vision, has gained c...

Descripción completa

Detalles Bibliográficos
Autores: Bekhouche, Salah Eddine, Benlamoudi, Azeddine, Dornaika, Fadi, Telli, Hichem, Bounab, Yazid
Tipo de recurso: artículo
Fecha de publicación:2024
País:España
Institución:Universidad del País Vasco
Repositorio:Addi. Archivo Digital para la Docencia y la Investigación
OAI Identifier:oai:addi.ehu.eus:10810/69346
Acceso en línea:http://hdl.handle.net/10810/69346
Access Level:acceso abierto
Palabra clave:age estimation
deep learning
multilevel deep features
adaptive regression
id ES_f6c2b1ffaff55d6478209db7fca9e154
oai_identifier_str oai:addi.ehu.eus:10810/69346
network_acronym_str ES
network_name_str España
repository_id_str
spelling Facial Age Estimation Using Multi-Stage Deep Neural NetworksBekhouche, Salah EddineBenlamoudi, AzeddineDornaika, FadiTelli, HichemBounab, Yazidage estimationdeep learningmultilevel deep featuresadaptive regressionOver the last decade, the world has witnessed many breakthroughs in artificial intelligence, largely due to advances in deep learning technology. Notably, computer vision solutions have significantly contributed to these achievements. Human face analysis, a core area of computer vision, has gained considerable attention due to its wide applicability in fields such as law enforcement, social media, and marketing. However, existing methods for facial age estimation often struggle with accuracy due to limited feature extraction capabilities and inefficiencies in learning hierarchical representations. This paper introduces a novel framework to address these issues by proposing a Multi-Stage Deep Neural Network (MSDNN) architecture. The MSDNN architecture divides each CNN backbone into multiple stages, enabling more comprehensive feature extraction, thereby improving the accuracy of age predictions from facial images. Our framework demonstrates a significant performance improvement over traditional solutions, with its effectiveness validated through comparisons with the EfficientNet and MobileNetV3 architectures. The proposed MSDNN architecture achieves a notable decrease in Mean Absolute Error (MAE) across three widely used public datasets (MORPH2, CACD, and AFAD) while maintaining a virtually identical parameter count compared to the initial backbone architectures. These results underscore the effectiveness and feasibility of our methodology in advancing the field of age estimation, showcasing it as a robust solution for enhancing the accuracy of age prediction algorithms.This work was partially supported by grant PID2021-126701OB-I00 funded by MCIN/AEI/10.13039/501100011033 and by ‘ERDF: A way of making Europe’.MDPI2024202420242024info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10810/69346reponame:Addi. Archivo Digital para la Docencia y la Investigacióninstname:Universidad del País VascoInglésinfo:eu-repo/grantAgreement/MICINN/PID2021-126701OB-I00/https://www.mdpi.com/2079-9292/13/16/3259info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by/4.0/es/© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/ 4.0/).oai:addi.ehu.eus:10810/693462026-06-18T09:23:17Z
dc.title.none.fl_str_mv Facial Age Estimation Using Multi-Stage Deep Neural Networks
title Facial Age Estimation Using Multi-Stage Deep Neural Networks
spellingShingle Facial Age Estimation Using Multi-Stage Deep Neural Networks
Bekhouche, Salah Eddine
age estimation
deep learning
multilevel deep features
adaptive regression
title_short Facial Age Estimation Using Multi-Stage Deep Neural Networks
title_full Facial Age Estimation Using Multi-Stage Deep Neural Networks
title_fullStr Facial Age Estimation Using Multi-Stage Deep Neural Networks
title_full_unstemmed Facial Age Estimation Using Multi-Stage Deep Neural Networks
title_sort Facial Age Estimation Using Multi-Stage Deep Neural Networks
dc.creator.none.fl_str_mv Bekhouche, Salah Eddine
Benlamoudi, Azeddine
Dornaika, Fadi
Telli, Hichem
Bounab, Yazid
author Bekhouche, Salah Eddine
author_facet Bekhouche, Salah Eddine
Benlamoudi, Azeddine
Dornaika, Fadi
Telli, Hichem
Bounab, Yazid
author_role author
author2 Benlamoudi, Azeddine
Dornaika, Fadi
Telli, Hichem
Bounab, Yazid
author2_role author
author
author
author
dc.subject.none.fl_str_mv age estimation
deep learning
multilevel deep features
adaptive regression
topic age estimation
deep learning
multilevel deep features
adaptive regression
description Over the last decade, the world has witnessed many breakthroughs in artificial intelligence, largely due to advances in deep learning technology. Notably, computer vision solutions have significantly contributed to these achievements. Human face analysis, a core area of computer vision, has gained considerable attention due to its wide applicability in fields such as law enforcement, social media, and marketing. However, existing methods for facial age estimation often struggle with accuracy due to limited feature extraction capabilities and inefficiencies in learning hierarchical representations. This paper introduces a novel framework to address these issues by proposing a Multi-Stage Deep Neural Network (MSDNN) architecture. The MSDNN architecture divides each CNN backbone into multiple stages, enabling more comprehensive feature extraction, thereby improving the accuracy of age predictions from facial images. Our framework demonstrates a significant performance improvement over traditional solutions, with its effectiveness validated through comparisons with the EfficientNet and MobileNetV3 architectures. The proposed MSDNN architecture achieves a notable decrease in Mean Absolute Error (MAE) across three widely used public datasets (MORPH2, CACD, and AFAD) while maintaining a virtually identical parameter count compared to the initial backbone architectures. These results underscore the effectiveness and feasibility of our methodology in advancing the field of age estimation, showcasing it as a robust solution for enhancing the accuracy of age prediction algorithms.
publishDate 2024
dc.date.none.fl_str_mv 2024
2024
2024
2024
dc.type.none.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10810/69346
url http://hdl.handle.net/10810/69346
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv info:eu-repo/grantAgreement/MICINN/PID2021-126701OB-I00/
https://www.mdpi.com/2079-9292/13/16/3259
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by/4.0/es/
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by/4.0/es/
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:Addi. Archivo Digital para la Docencia y la Investigación
instname:Universidad del País Vasco
instname_str Universidad del País Vasco
reponame_str Addi. Archivo Digital para la Docencia y la Investigación
collection Addi. Archivo Digital para la Docencia y la Investigación
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869424792808980480
score 15,812455

Similares en LA Referencia