Optimizing Age Estimation in Facial Images with Advanced Multi-Class Classification Techniques

Automatic age and gender prediction from facial images is increasingly crucial for applications in security, marketing, and social media. Existing systems often face challenges related to accuracy, demographic generalization, and bias. This study addresses these issues by developing a deep learni...

Full description

Bibliographic Details
Main Authors:	R., Karthickmanoj, S.Aasha, Nandhini, D., Lakshmi, R., Rajasree
Format:	Article
Language:	English English
Published:	INTI International University 2024
Subjects:	Q Science (General) QA Mathematics QA75 Electronic computers. Computer science QA76 Computer software
Online Access:	http://eprints.intimal.edu.my/1982/ http://eprints.intimal.edu.my/1982/1/521 http://eprints.intimal.edu.my/1982/2/joit2024_08b.pdf

_version_	1848766888394358784
author	R., Karthickmanoj S.Aasha, Nandhini D., Lakshmi R., Rajasree
author_facet	R., Karthickmanoj S.Aasha, Nandhini D., Lakshmi R., Rajasree
author_sort	R., Karthickmanoj
building	INTI Institutional Repository
collection	Online Access
description	Automatic age and gender prediction from facial images is increasingly crucial for applications in security, marketing, and social media. Existing systems often face challenges related to accuracy, demographic generalization, and bias. This study addresses these issues by developing a deep learning-based system utilizing Convolutional Neural Networks (CNNs) for enhanced classification of age and gender. The key research gaps include limited accuracy, insufficient handling of diverse data, and model bias. The proposed approach encompasses data acquisition, preprocessing, and the design of a CNN architecture within a multi-class classification framework. Various CNN models are evaluated, incorporating transfer learning, hyperparameter optimization, and regularization techniques to improve performance. The system's effectiveness is assessed through metrics such as classification accuracy, precision, recall, and robustness across different demographic groups. Results indicate significant advancements in prediction accuracy and model generalization compared to existing methods. The technology holds practical applications in security, personalized marketing, and social networking. Challenges such as model bias and the need for diverse datasets are addressed, with future research aimed at further refining the model and expanding its applicability. This work highlights the substantial improvements deep learning offers to facial recognition technologies.
first_indexed	2025-11-14T11:58:18Z
format	Article
id	intimal-1982
institution	INTI International University
institution_category	Local University
language	English English
last_indexed	2025-11-14T11:58:18Z
publishDate	2024
publisher	INTI International University
recordtype	eprints
repository_type	Digital Repository
spelling	intimal-19822025-06-13T03:15:21Z http://eprints.intimal.edu.my/1982/ Optimizing Age Estimation in Facial Images with Advanced Multi-Class Classification Techniques R., Karthickmanoj S.Aasha, Nandhini D., Lakshmi R., Rajasree Q Science (General) QA Mathematics QA75 Electronic computers. Computer science QA76 Computer software Automatic age and gender prediction from facial images is increasingly crucial for applications in security, marketing, and social media. Existing systems often face challenges related to accuracy, demographic generalization, and bias. This study addresses these issues by developing a deep learning-based system utilizing Convolutional Neural Networks (CNNs) for enhanced classification of age and gender. The key research gaps include limited accuracy, insufficient handling of diverse data, and model bias. The proposed approach encompasses data acquisition, preprocessing, and the design of a CNN architecture within a multi-class classification framework. Various CNN models are evaluated, incorporating transfer learning, hyperparameter optimization, and regularization techniques to improve performance. The system's effectiveness is assessed through metrics such as classification accuracy, precision, recall, and robustness across different demographic groups. Results indicate significant advancements in prediction accuracy and model generalization compared to existing methods. The technology holds practical applications in security, personalized marketing, and social networking. Challenges such as model bias and the need for diverse datasets are addressed, with future research aimed at further refining the model and expanding its applicability. This work highlights the substantial improvements deep learning offers to facial recognition technologies. INTI International University 2024-08 Article PeerReviewed text en cc_by_4 http://eprints.intimal.edu.my/1982/1/521 text en cc_by_4 http://eprints.intimal.edu.my/1982/2/joit2024_08b.pdf R., Karthickmanoj and S.Aasha, Nandhini and D., Lakshmi and R., Rajasree (2024) Optimizing Age Estimation in Facial Images with Advanced Multi-Class Classification Techniques. Journal of Innovation and Technology, 2024 (08). pp. 1-7. ISSN 2805-5179 http://ipublishing.intimal.edu.my/joint.html
spellingShingle	Q Science (General) QA Mathematics QA75 Electronic computers. Computer science QA76 Computer software R., Karthickmanoj S.Aasha, Nandhini D., Lakshmi R., Rajasree Optimizing Age Estimation in Facial Images with Advanced Multi-Class Classification Techniques
title	Optimizing Age Estimation in Facial Images with Advanced Multi-Class Classification Techniques
title_full	Optimizing Age Estimation in Facial Images with Advanced Multi-Class Classification Techniques
title_fullStr	Optimizing Age Estimation in Facial Images with Advanced Multi-Class Classification Techniques
title_full_unstemmed	Optimizing Age Estimation in Facial Images with Advanced Multi-Class Classification Techniques
title_short	Optimizing Age Estimation in Facial Images with Advanced Multi-Class Classification Techniques
title_sort	optimizing age estimation in facial images with advanced multi-class classification techniques
topic	Q Science (General) QA Mathematics QA75 Electronic computers. Computer science QA76 Computer software
url	http://eprints.intimal.edu.my/1982/ http://eprints.intimal.edu.my/1982/ http://eprints.intimal.edu.my/1982/1/521 http://eprints.intimal.edu.my/1982/2/joit2024_08b.pdf

Optimizing Age Estimation in Facial Images with Advanced Multi-Class Classification Techniques

Similar Items