Please read our paper: Mohamed Loey, Gunasekaran Manogaran, Mohamed Hamed N. Taha, Nour Eldeen M. Khalifa, Fighting against COVID-19: A novel deep learning model based on YOLO-v2 with ResNet-50 for medical face mask detection, Sustainable Cities and Society, Volume 65, 2021, https://doi.org/10.1016/j.scs.2020.102600

Mohamed Loey, Gunasekaran Manogaran, Mohamed Hamed N. Taha, Nour Eldeen M. Khalifa, A hybrid deep transfer learning model with machine learning methods for face mask detection in the era of the COVID-19 pandemic, Measurement, Volume 167, 2021, https://doi.org/10.1016/j.measurement.2020.108288

Abstract

Deep learning has shown tremendous potential in many real-life applications in different domains. One of these potentials is object detection. Recent object detection which is based on deep learning models has achieved promising results concerning the finding of an object in images. The objective of this paper is to annotate and localize the medical face mask objects in real-life images. Wearing a medical face mask in public areas, protect people from COVID-19 transmission among them. The proposed model consists of two components. The first component is designed for the feature extraction process based on the ResNet-50 deep transfer learning model. While the second component is designed for the detection of medical face masks based on YOLO v2. Two medical face masks datasets have been combined in one dataset to be investigated through this research. To improve the object detection process, mean IoU has been used to estimate the best number of anchor boxes. The achieved results concluded that the adam optimizer achieved the highest average precision percentage of 81% as a detector. Finally, a comparative result with related work has been presented at the end of the research. The proposed detector achieved higher accuracy and precision than the related work.

Context

This Dataset conducted its experiments based on two public medical face mask datasets. The first dataset is Medical Masks Dataset (MMD)published by Mikolaj Witkowski (https://www.kaggle.com/vtech6/me dical-masks-dataset). The MMD dataset consists of 682 pictures with over 3k medical masked faces wearing masks. The second public masked face dataset is a Face Mask Dataset (FMD)in (https://www.kaggle.com/andrewmvd/face-mask-detection). The FMD dataset consists of 853 images. We created a new dataset by combining MMD and FMD. The merged dataset contains 1415 images by removing bad quality images and redundancy

Acknowledgements

Cite our papers: Mohamed Loey, Gunasekaran Manogaran, Mohamed Hamed N. Taha, Nour Eldeen M. Khalifa, Fighting against COVID-19: A novel deep learning model based on YOLO-v2 with ResNet-50 for medical face mask detection, Sustainable Cities and Society, Volume 65, 2021, https://doi.org/10.1016/j.scs.2020.102600

Mohamed Loey, Gunasekaran Manogaran, Mohamed Hamed N. Taha, Nour Eldeen M. Khalifa, A hybrid deep transfer learning model with machine learning methods for face mask detection in the era of the COVID-19 pandemic, Measurement, Volume 167, 2021, https://doi.org/10.1016/j.measurement.2020.108288

Loey, M., Manogaran, G. & Khalifa, N.E.M. A deep transfer learning model with classical data augmentation and CGAN to detect COVID-19 from chest CT radiography digital images. Neural Comput & Applic (2020). https://doi.org/10.1007/s00521-020-05437-x Loey, Mohamed; Smarandache, Florentin; M. Khalifa, Nour E. 2020. "Within the Lack of Chest COVID-19 X-ray Dataset: A Novel Detection Model Based on GAN and Deep Transfer Learning" Symmetry 12, no. 4: 651. https://doi.org/10.3390/sym12040651 Khalifa, N.E.M., Smarandache, F., Manogaran, G. et al. A Study of the Neutrosophic Set Significance on Deep Transfer Learning Models: an Experimental Case on a Limited COVID-19 Chest X-ray Dataset. Cogn Comput (2021). https://doi.org/10.1007/s12559-020-09802-9

Inspiration

Creating the proposed database presents more challenges Benha University http://bu.edu.eg/staff/mloey https://mloey.github.io/ https://orcid.org/0000-0002-3849-4566 Arabic Handwritten Characters Dataset https://www.kaggle.com/mloey1/ahcd1 Arabic Handwritten Digits Dataset https://www.kaggle.com/mloey1/ahdd1

Original dataset source: https://www.kaggle.com/datasets/andrewmvd/face-mask-detection/discussion

This dataset contains three class: mask_weared_incorrect, with_mask, without_mask

Proclaim: I personally don't own the source dataset itself, only augmentations are applied for model training.

In this study, photographs of mask (name start 1), no mask (name start 2), and improper mask (name start 3) were collected by researchers via internet search. The discovered photos were combined with 4072 photos that were uploaded to the Kaggle website by Larxel (https://www.kaggle.com/andrewmvd/face-mask-detection). A face detection application was created to obtain face images from all the photos in the database. There may be more than one photo of the same individual in the database. This program, coded in C# language, detected automatically faces from photos. Through visual inspection, we eliminated a few low-quality face-mask images. Finally, we collected 529 improper mask, 992 mask, and 554 no mask face images. The used dataset contains 2075 facial images taken from different profiles. By using this dataset, a model for face mask-wearing sensitive doors has been proposed. Moreover, this dataset is a hybrid dataset. We created this facial image dataset using open-source face mask datasets. The most important attribute that distinguishes this dataset from other datasets is the creation of the improper mask class.

In order to use the dataset here, the following article must be cited.

• AYDEMİR, E., YALÇINKAYA, M. A., Barua, P. D., BAYĞIN, M., Faust, O., DOĞAN, Ş., … Udyavara, R. A. (2022). Hybrid Deep Feature Generation for Appropriate Face Mask Use Detection. International Journal of Environmental Research and Public Health, 19(4), Doi: https://dx.doi.org/10.3390/ijerph19041939

The image source of this dataset is from https://www.kaggle.com/datasets/andrewmvd/face-mask-detection .

This dataset is a labeled subset of a larger dataset originally sourced from Kaggle. We used Label Studio to annotate a portion of the original data, focusing on a specific task.

This partially annotated dataset is intended to serve as a starting point for relevant research and model training.

Original Dataset https://www.kaggle.com/datasets/andrewmvd/face-mask-detection

Images collected from:

• https://www.kaggle.com/aditya276/face-mask-dataset-yolo-format
• https://www.kaggle.com/andrewmvd/face-mask-detection
• https://www.kaggle.com/alexandralorenzo/maskdetection
• http://shuoyang1213.me/WIDERFACE/

Context

Having seen multiple datasets related to face mask detection on Kaggle, one dataset which stood out contained 3 classes (with mask, without a mask, and wearing mask incorrectly), unfortunately, the dataset was highly imbalanced and uncleaned. So to improve this dataset, images had to be augmented in such a way that each class has an equal distribution of images and removing noisy images which could be considered as outliers. Thus this dataset that I've created is a combination of an existing dataset that has been cleaned and equally distributed across each class.

Content

The dataset contains 3 folders labeled as to which class they belong to. the 3 classes are "with_mask", "withou_mask", and "mask_weared_incorrect". Each folder holds 2994 images of people that belong to such a labeled class.

Acknowledgements

I would like to acknowledge the usage of those 2 datasets: - https://www.kaggle.com/ashishjangra27/face-mask-12k-images-dataset - https://www.kaggle.com/andrewmvd/face-mask-detection

Using the above-mentioned datasets, data was manually extracted from both datasets in such a way that the new dataset is equally distributed and contains good quality samples without noise.