An Optimized Machine Learning and Deep Learning Framework for Facial and Masked Facial Recognition
In this study, we aimed to find an optimized approach to improving facial and masked facial recognition using machine learning and deep learning techniques. Prior studies only used a single machine learning model for classification and did not report optimal parameter values. In contrast, we utilize...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ital Publication
2023-07-01
|
| Series: | Emerging Science Journal |
| Subjects: | |
| Online Access: | https://www.ijournalse.org/index.php/ESJ/article/view/1813 |
| _version_ | 1827895656887353344 |
|---|---|
| author | Putthiporn Thanathamathee Siriporn Sawangarreerak Prateep Kongkla Dinna Nina Mohd Nizam |
| author_facet | Putthiporn Thanathamathee Siriporn Sawangarreerak Prateep Kongkla Dinna Nina Mohd Nizam |
| author_sort | Putthiporn Thanathamathee |
| collection | DOAJ |
| description | In this study, we aimed to find an optimized approach to improving facial and masked facial recognition using machine learning and deep learning techniques. Prior studies only used a single machine learning model for classification and did not report optimal parameter values. In contrast, we utilized a grid search with hyperparameter tuning and nested cross-validation to achieve better results during the verification phase. We performed experiments on a large dataset of facial images with and without masks. Our findings showed that the SVM model with hyperparameter tuning had the highest accuracy compared to other models, achieving a recognition accuracy of 0.99912. The precision values for recognition without masks and with masks were 0.99925 and 0.98417, respectively. We tested our approach in real-life scenarios and found that it accurately identified masked individuals through facial recognition. Furthermore, our study stands out from others as it incorporates hyperparameter tuning and nested cross-validation during the verification phase to enhance the model's performance, generalization, and robustness while optimizing data utilization. Our optimized approach has potential implications for improving security systems in various domains, including public safety and healthcare. |
| first_indexed | 2024-03-12T22:24:54Z |
| format | Article |
| id | doaj.art-a4205e22a0b74ee0ab42ed1cb99af541 |
| institution | Directory Open Access Journal |
| issn | 2610-9182 |
| language | English |
| last_indexed | 2024-03-12T22:24:54Z |
| publishDate | 2023-07-01 |
| publisher | Ital Publication |
| record_format | Article |
| series | Emerging Science Journal |
| spelling | doaj.art-a4205e22a0b74ee0ab42ed1cb99af5412023-07-22T11:51:16ZengItal PublicationEmerging Science Journal2610-91822023-07-01741173118710.28991/ESJ-2023-07-04-010515An Optimized Machine Learning and Deep Learning Framework for Facial and Masked Facial RecognitionPutthiporn Thanathamathee0Siriporn Sawangarreerak1Prateep Kongkla2Dinna Nina Mohd Nizam3School of Engineering and Technology, Walailak University, Nakhon Si Thammarat 80160,School of Accountancy and Finance, Walailak University, Nakhon Si Thammarat 80160,School of Engineering and Technology, Walailak University, Nakhon Si Thammarat 80160,User Experience Research Group, Faculty of Computing and Informatics, Universiti Malaysia Sabah, 87000 W.P.Labuan,In this study, we aimed to find an optimized approach to improving facial and masked facial recognition using machine learning and deep learning techniques. Prior studies only used a single machine learning model for classification and did not report optimal parameter values. In contrast, we utilized a grid search with hyperparameter tuning and nested cross-validation to achieve better results during the verification phase. We performed experiments on a large dataset of facial images with and without masks. Our findings showed that the SVM model with hyperparameter tuning had the highest accuracy compared to other models, achieving a recognition accuracy of 0.99912. The precision values for recognition without masks and with masks were 0.99925 and 0.98417, respectively. We tested our approach in real-life scenarios and found that it accurately identified masked individuals through facial recognition. Furthermore, our study stands out from others as it incorporates hyperparameter tuning and nested cross-validation during the verification phase to enhance the model's performance, generalization, and robustness while optimizing data utilization. Our optimized approach has potential implications for improving security systems in various domains, including public safety and healthcare.https://www.ijournalse.org/index.php/ESJ/article/view/1813masked face recognitiondeep learninghyperparameter tuninggrid searchnested cross-validation. |
| spellingShingle | Putthiporn Thanathamathee Siriporn Sawangarreerak Prateep Kongkla Dinna Nina Mohd Nizam An Optimized Machine Learning and Deep Learning Framework for Facial and Masked Facial Recognition Emerging Science Journal masked face recognition deep learning hyperparameter tuning grid search nested cross-validation. |
| title | An Optimized Machine Learning and Deep Learning Framework for Facial and Masked Facial Recognition |
| title_full | An Optimized Machine Learning and Deep Learning Framework for Facial and Masked Facial Recognition |
| title_fullStr | An Optimized Machine Learning and Deep Learning Framework for Facial and Masked Facial Recognition |
| title_full_unstemmed | An Optimized Machine Learning and Deep Learning Framework for Facial and Masked Facial Recognition |
| title_short | An Optimized Machine Learning and Deep Learning Framework for Facial and Masked Facial Recognition |
| title_sort | optimized machine learning and deep learning framework for facial and masked facial recognition |
| topic | masked face recognition deep learning hyperparameter tuning grid search nested cross-validation. |
| url | https://www.ijournalse.org/index.php/ESJ/article/view/1813 |
| work_keys_str_mv | AT putthipornthanathamathee anoptimizedmachinelearninganddeeplearningframeworkforfacialandmaskedfacialrecognition AT siripornsawangarreerak anoptimizedmachinelearninganddeeplearningframeworkforfacialandmaskedfacialrecognition AT prateepkongkla anoptimizedmachinelearninganddeeplearningframeworkforfacialandmaskedfacialrecognition AT dinnaninamohdnizam anoptimizedmachinelearninganddeeplearningframeworkforfacialandmaskedfacialrecognition AT putthipornthanathamathee optimizedmachinelearninganddeeplearningframeworkforfacialandmaskedfacialrecognition AT siripornsawangarreerak optimizedmachinelearninganddeeplearningframeworkforfacialandmaskedfacialrecognition AT prateepkongkla optimizedmachinelearninganddeeplearningframeworkforfacialandmaskedfacialrecognition AT dinnaninamohdnizam optimizedmachinelearninganddeeplearningframeworkforfacialandmaskedfacialrecognition |