Improving the Accuracy of Gender Classification Based on Skin Tone Using Convolutional Neural Network: Transfer Learning (CNN-TL)

Gender classification is one of the key features in soft biometrics besides age, ethnicity, facial expression, etc. Gender classification based on skin tone has its own importance that can further improve the performance of facial recognition systems. Most Convolutional Neural Network (CNN) models r...

Full description

Bibliographic Details
Published in:Lecture Notes in Electrical Engineering
Main Author: Mustapha M.F.; Mohamad N.M.; Ab Hamid S.H.; Abdul Aziz N.A.S.
Format: Conference paper
Language:English
Published: Springer Science and Business Media Deutschland GmbH 2024
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85190359136&doi=10.1007%2f978-981-99-9005-4_62&partnerID=40&md5=9183111e67e178912685cecebf95d589
id 2-s2.0-85190359136
spelling 2-s2.0-85190359136
Mustapha M.F.; Mohamad N.M.; Ab Hamid S.H.; Abdul Aziz N.A.S.
Improving the Accuracy of Gender Classification Based on Skin Tone Using Convolutional Neural Network: Transfer Learning (CNN-TL)
2024
Lecture Notes in Electrical Engineering
1123 LNEE

10.1007/978-981-99-9005-4_62
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85190359136&doi=10.1007%2f978-981-99-9005-4_62&partnerID=40&md5=9183111e67e178912685cecebf95d589
Gender classification is one of the key features in soft biometrics besides age, ethnicity, facial expression, etc. Gender classification based on skin tone has its own importance that can further improve the performance of facial recognition systems. Most Convolutional Neural Network (CNN) models require a large amount of training data to improve classification accuracy and increase processing time. Fortunately, the MobileNetV2 model overcomes this problem by running faster than the other models. However, the model’s accuracy suffers when the gender classification results based on skin tone reach 50% accuracy, indicating that the model suffers from an “overfitting” problem. To address this issue, the proposed research constructed a novel face images dataset containing 6250 face images that chosen from original FaceARG dataset and divided equally into Bright (3125) and Dark (3125) skin tone. Each skin tone (Bright and Dark) is equally divided into two genders, 1563 (male) and 1563 (female). The new FaceARG dataset is then used to run two types of experiments (Bright and Dark) on the MobileNetV2 model. The Fine-Tuning method from Transfer Learning is then applied to the MobileNetV2 model, along with method gains from previous studies. The Dark experiment achieved the highest accuracy on training dataset, which is 97.4%, compared to 50% on the model without fine-tuning, and the Bright experiment achieved the highest accuracy on test dataset, which is 89.8%, compared to 50% on the model without fine-tuning. The findings of this study will determine the ability of the proposed model to accurately classify gender based on skin tone. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.
Springer Science and Business Media Deutschland GmbH
18761100
English
Conference paper

author Mustapha M.F.; Mohamad N.M.; Ab Hamid S.H.; Abdul Aziz N.A.S.
spellingShingle Mustapha M.F.; Mohamad N.M.; Ab Hamid S.H.; Abdul Aziz N.A.S.
Improving the Accuracy of Gender Classification Based on Skin Tone Using Convolutional Neural Network: Transfer Learning (CNN-TL)
author_facet Mustapha M.F.; Mohamad N.M.; Ab Hamid S.H.; Abdul Aziz N.A.S.
author_sort Mustapha M.F.; Mohamad N.M.; Ab Hamid S.H.; Abdul Aziz N.A.S.
title Improving the Accuracy of Gender Classification Based on Skin Tone Using Convolutional Neural Network: Transfer Learning (CNN-TL)
title_short Improving the Accuracy of Gender Classification Based on Skin Tone Using Convolutional Neural Network: Transfer Learning (CNN-TL)
title_full Improving the Accuracy of Gender Classification Based on Skin Tone Using Convolutional Neural Network: Transfer Learning (CNN-TL)
title_fullStr Improving the Accuracy of Gender Classification Based on Skin Tone Using Convolutional Neural Network: Transfer Learning (CNN-TL)
title_full_unstemmed Improving the Accuracy of Gender Classification Based on Skin Tone Using Convolutional Neural Network: Transfer Learning (CNN-TL)
title_sort Improving the Accuracy of Gender Classification Based on Skin Tone Using Convolutional Neural Network: Transfer Learning (CNN-TL)
publishDate 2024
container_title Lecture Notes in Electrical Engineering
container_volume 1123 LNEE
container_issue
doi_str_mv 10.1007/978-981-99-9005-4_62
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85190359136&doi=10.1007%2f978-981-99-9005-4_62&partnerID=40&md5=9183111e67e178912685cecebf95d589
description Gender classification is one of the key features in soft biometrics besides age, ethnicity, facial expression, etc. Gender classification based on skin tone has its own importance that can further improve the performance of facial recognition systems. Most Convolutional Neural Network (CNN) models require a large amount of training data to improve classification accuracy and increase processing time. Fortunately, the MobileNetV2 model overcomes this problem by running faster than the other models. However, the model’s accuracy suffers when the gender classification results based on skin tone reach 50% accuracy, indicating that the model suffers from an “overfitting” problem. To address this issue, the proposed research constructed a novel face images dataset containing 6250 face images that chosen from original FaceARG dataset and divided equally into Bright (3125) and Dark (3125) skin tone. Each skin tone (Bright and Dark) is equally divided into two genders, 1563 (male) and 1563 (female). The new FaceARG dataset is then used to run two types of experiments (Bright and Dark) on the MobileNetV2 model. The Fine-Tuning method from Transfer Learning is then applied to the MobileNetV2 model, along with method gains from previous studies. The Dark experiment achieved the highest accuracy on training dataset, which is 97.4%, compared to 50% on the model without fine-tuning, and the Bright experiment achieved the highest accuracy on test dataset, which is 89.8%, compared to 50% on the model without fine-tuning. The findings of this study will determine the ability of the proposed model to accurately classify gender based on skin tone. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.
publisher Springer Science and Business Media Deutschland GmbH
issn 18761100
language English
format Conference paper
accesstype
record_format scopus
collection Scopus
_version_ 1818940556244418560