Deep Learning Models for Automatic Makeup Detection
Makeup can disguise facial features, which results in degradation in the performance of many facial-related analysis systems, including face recognition, facial landmark characterisation, aesthetic quantification and automated age estimation methods. Thus, facial makeup is likely to directly affect...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | AI |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-2688/2/4/31 |
| _version_ | 1797506984686125056 |
|---|---|
| author | Theiab Alzahrani Baidaa Al-Bander Waleed Al-Nuaimy |
| author_facet | Theiab Alzahrani Baidaa Al-Bander Waleed Al-Nuaimy |
| author_sort | Theiab Alzahrani |
| collection | DOAJ |
| description | Makeup can disguise facial features, which results in degradation in the performance of many facial-related analysis systems, including face recognition, facial landmark characterisation, aesthetic quantification and automated age estimation methods. Thus, facial makeup is likely to directly affect several real-life applications such as cosmetology and virtual cosmetics recommendation systems, security and access control, and social interaction. In this work, we conduct a comparative study and design automated facial makeup detection systems leveraging multiple learning schemes from a single unconstrained photograph. We have investigated and studied the efficacy of deep learning models for makeup detection incorporating the use of transfer learning strategy with semi-supervised learning using labelled and unlabelled data. First, during the supervised learning, the VGG16 convolution neural network, pre-trained on a large dataset, is fine-tuned on makeup labelled data. Secondly, two unsupervised learning methods, which are self-learning and convolutional auto-encoder, are trained on unlabelled data and then incorporated with supervised learning during semi-supervised learning. Comprehensive experiments and comparative analysis have been conducted on 2479 labelled images and 446 unlabelled images collected from six challenging makeup datasets. The obtained results reveal that the convolutional auto-encoder merged with supervised learning gives the best makeup detection performance achieving an accuracy of 88.33% and area under ROC curve of 95.15%. The promising results obtained from conducted experiments reveal and reflect the efficiency of combining different learning strategies by harnessing labelled and unlabelled data. It would also be advantageous to the beauty industry to develop such computational intelligence methods. |
| first_indexed | 2024-03-10T04:40:15Z |
| format | Article |
| id | doaj.art-23804649723344e88e534b0a7537bbf9 |
| institution | Directory Open Access Journal |
| issn | 2673-2688 |
| language | English |
| last_indexed | 2024-03-10T04:40:15Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | AI |
| spelling | doaj.art-23804649723344e88e534b0a7537bbf92023-11-23T03:24:26ZengMDPI AGAI2673-26882021-10-012449751110.3390/ai2040031Deep Learning Models for Automatic Makeup DetectionTheiab Alzahrani0Baidaa Al-Bander1Waleed Al-Nuaimy2Department of Electrical Engineering and Electronics, University of Liverpool, Liverpool L69 3GJ, UKDepartment of Computer Engineering, University of Diyala, Baqubah 32010, IraqDepartment of Electrical Engineering and Electronics, University of Liverpool, Liverpool L69 3GJ, UKMakeup can disguise facial features, which results in degradation in the performance of many facial-related analysis systems, including face recognition, facial landmark characterisation, aesthetic quantification and automated age estimation methods. Thus, facial makeup is likely to directly affect several real-life applications such as cosmetology and virtual cosmetics recommendation systems, security and access control, and social interaction. In this work, we conduct a comparative study and design automated facial makeup detection systems leveraging multiple learning schemes from a single unconstrained photograph. We have investigated and studied the efficacy of deep learning models for makeup detection incorporating the use of transfer learning strategy with semi-supervised learning using labelled and unlabelled data. First, during the supervised learning, the VGG16 convolution neural network, pre-trained on a large dataset, is fine-tuned on makeup labelled data. Secondly, two unsupervised learning methods, which are self-learning and convolutional auto-encoder, are trained on unlabelled data and then incorporated with supervised learning during semi-supervised learning. Comprehensive experiments and comparative analysis have been conducted on 2479 labelled images and 446 unlabelled images collected from six challenging makeup datasets. The obtained results reveal that the convolutional auto-encoder merged with supervised learning gives the best makeup detection performance achieving an accuracy of 88.33% and area under ROC curve of 95.15%. The promising results obtained from conducted experiments reveal and reflect the efficiency of combining different learning strategies by harnessing labelled and unlabelled data. It would also be advantageous to the beauty industry to develop such computational intelligence methods.https://www.mdpi.com/2673-2688/2/4/31makeup detectiondeep learningconvolution neural networkssemi-supervised learningauto-encoderself-learning |
| spellingShingle | Theiab Alzahrani Baidaa Al-Bander Waleed Al-Nuaimy Deep Learning Models for Automatic Makeup Detection AI makeup detection deep learning convolution neural networks semi-supervised learning auto-encoder self-learning |
| title | Deep Learning Models for Automatic Makeup Detection |
| title_full | Deep Learning Models for Automatic Makeup Detection |
| title_fullStr | Deep Learning Models for Automatic Makeup Detection |
| title_full_unstemmed | Deep Learning Models for Automatic Makeup Detection |
| title_short | Deep Learning Models for Automatic Makeup Detection |
| title_sort | deep learning models for automatic makeup detection |
| topic | makeup detection deep learning convolution neural networks semi-supervised learning auto-encoder self-learning |
| url | https://www.mdpi.com/2673-2688/2/4/31 |
| work_keys_str_mv | AT theiabalzahrani deeplearningmodelsforautomaticmakeupdetection AT baidaaalbander deeplearningmodelsforautomaticmakeupdetection AT waleedalnuaimy deeplearningmodelsforautomaticmakeupdetection |