Context The goal of this dataset is to provide quality images for face mask detection AI & ML projects. Also to provide a model for facemask detection project.

Content The dataset contains around 3835 images under mask and no mask directories.

Acknowledgements The data was scraped from images from several search engines.

Inspiration I would like people to use this dataset to create mask detection models which will help our universe to protect from COVID-19.

Explore the Mask Detection Dataset with 6000 diverse images of people wearing masks, scarves.

The dataset used for training the model included a combination of open-source datasets from Kaggle's Medical Mask Dataset and PyImageSearch by Mikolaj Witkowski and Prajna Bhandary. The Kaggle dataset had 678 images of people wearing medical masks, while the PyImageSearch dataset had 1,376 images divided into two classes: wearing masks (690) and without masks (686). The datasets were enhanced with facial landmarks to create a balanced dataset of 5521 images, useful for identifying individuals wearing masks during illegal activities.

Medical Mask Detection

## Overview

Medical Mask Detection is a dataset for object detection tasks - it contains Masks annotations for 4,837 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Here are a few use cases for this project:

1. Public Health Monitoring: This model can be used in public spaces such as airports, train stations, or shopping malls to monitor mask usage among people, ensuring that individuals are adhering to public health guidelines and wearing masks correctly.

2. Workplace Compliance: Businesses, particularly health-care facilities, food production plants, and office spaces, can utilize this model to maintain workplace safety and compliance with mandated mask-wearing protocols.

3. Education and Training: The model can be incorporated into educational programs or apps to provide visual training and feedback on the correct way to wear a mask, fostering COVID-19 preventive practices.

4. Video Surveillance Enhancement: Integrated with existing CCTV systems, this computer vision model could facilitate real-time identification of individuals without masks or wearing masks improperly, aiding security personnel in maintaining health protocols.

5. Access Control Systems: It can be used to integrate with access control systems at locations like academic institutions, government buildings, or corporate offices. Entry could be denied or permitted based on whether the individual is wearing a mask and how it's worn.

A SARS-like coronavirus outbreak has been spreading in China since *************. To combat the virus which originated in Wuhan, the government has announced emergency measures including speeding up medical mask production. As of the end of April, 2020, China was producing around *********** medical masks daily, implying a steep rise in production capacity utilization rate. The country exported several billions of medical supplies as the coronavirus pandemic worsened across the world.

Dataset

This dataset was created by Shreyash Waghe

Contents

The Face Mask Wearing Image Dataset is a comprehensive collection of images focused on different types of face masks and their usage. This dataset has been meticulously organized and divided into two main folders: "Correct" and "Incorrect," representing instances of face masks being worn properly and improperly, respectively.

Correct: This folder contains images of individuals wearing face masks correctly. It comprises four subfolders, each representing a specific type of face mask: Bandana: Images of individuals wearing bandana-style face masks correctly. Cotton: Images of individuals wearing cloth or cotton face masks correctly. N95: Images of individuals wearing N95 respirators correctly. Surgical: Images of individuals wearing surgical masks correctly.

Incorrect: This folder contains images of individuals wearing face masks improperly. Like the "Correct" folder, it also comprises four subfolders corresponding to the different types of face masks: Bandana: Images of individuals wearing bandana-style face masks incorrectly. Cotton: Images of individuals wearing cloth or cotton face masks incorrectly. N95: Images of individuals wearing N95 respirators incorrectly. Surgical: Images of individuals wearing surgical masks incorrectly.

Within each of the above subfolders, there are three additional subfolders based on gender: Child: Images of children wearing the specific type of face mask (correctly or incorrectly). Male: Images of males wearing the specific type of face mask (correctly or incorrectly). Female: Images of females wearing the specific type of face mask (correctly or incorrectly). The dataset is designed to cover a diverse range of scenarios and variations in face mask usage across different mask types, age groups, and genders.

Total Images: The dataset contains a total of 24,916 images.

Usage: The Face Mask Wearing Image Dataset can be used for various research purposes, such as developing and evaluating machine learning algorithms for face mask detection and classification. Researchers can utilize this dataset to train models that can identify and differentiate between correct and incorrect face mask usage, contributing to public health initiatives, and promoting proper mask-wearing behavior.

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

U.S. medical mask market size to cross revenues of over $586 million by 2025, growing at a CAGR of over 23% during the forecast period. This industry analysis report includes a detailed segmentation by product, end-user, and geography, regional outlook, growth trends, competitive landscape, share & forecast, 2019–2025

From the site: Masks play a crucial role in protecting the health of individuals against respiratory diseases, as is one of the few precautions available for COVID-19 in the absence of immunization. With this dataset, it is possible to create a model to detect people wearing masks, not wearing them, or wearing masks improperly. This dataset contains 853 images belonging to the 3 classes, as well as their bounding boxes in the PASCAL VOC format. The classes are:

With mask; Without mask; Mask worn incorrectly.

In 2019, a SARS-like coronavirus COVID-19 outbreak has been spreading in China, driving the demand of face masks. According to a survey released in February 2020, about **** percent of the Chinese respondents stated that they had used *** to *** medical masks during the Chinese New Year.

Discover the booming market for printed medical masks! This in-depth analysis reveals key trends, market size projections (2025-2033), leading companies, and regional growth opportunities in this dynamic sector. Learn about the drivers, restraints, and segmentation shaping the future of personalized protective wear.

In 2019, China produced a total of ************ face masks. Since *************, a SARS-like coronavirus COVID-19 outbreak has been spreading in the country, driving the demand of medical masks. The production volume of medical masks was projected to double in 2020.

Face Mask Images Dataset

Dataset comprises 245,960 images of individuals captured in four different states of medical mask usage. Images feature varied lighting, angles, and demographics to ensure robust model generalization. It designed to train and evaluate detection models and mask detectors. Dataset enables advancements in biometric security, spoofing detection, and high-quality AI model development for real-world applications. - Get the data

  💵 Buy the Dataset: This… See the full description on the dataset page: https://huggingface.co/datasets/UniDataPro/medical-masks-image-dataset.

In 2024, the medical mask market size amounts to US$ 6,017.30 million and is probable to reach US$ 16,780.20 million by 2034, increase at a CAGR of 10.80%.

Attributes	Details
Market Value of Medical Mask for 2024	US$ 6,017.30 million
Projected Market Value for 2034	US$ 16,780.20 million
Value-based CAGR of Market for 2024 to 2034	10.80%

Category-wise Outlook

Attributes	Details
Product Type	Surgical mask
Market Share (2024)	41.1%

Attributes	Details
Application	Respiratory Safety
Market Share (2024)	40%

Country-wise Analysis

Countries	CAGR (2024 to 2034)
United State	8.30%
Germany	12.70%
Australia	8.50%
China	10.60%
Canada	12.10%

Context

This dataset based on Mikolaj Witkowski's dataset. Differences from the original: - All pictures are translated into jpg format. - All images contain only properly wearing medical masks - All annotation files are converted from xml to txt YOLO compatible format

Content

The following dataset contains pictures of people wearing medical masks along with txt files containing their descriptions. There are 632 pair overall.

Acknowledgements

This dataset based on Mikolaj Witkowski's Medical Masks Dataset . If my version was useful for you, please, upvote his as well.

The global printed medical masks market is projected for significant expansion, driven by increasing demand for personalized healthcare solutions and enhanced infection control measures. The market size is estimated to be around $8,500 million in 2025, with a projected Compound Annual Growth Rate (CAGR) of 12% through 2033. This growth is fueled by a confluence of factors, including heightened public awareness of hygiene protocols, the rising incidence of healthcare-associated infections, and the burgeoning trend of customization in consumer goods, which extends to personal protective equipment. The increasing adoption of printed medical masks in everyday public places, beyond traditional healthcare settings like hospitals and clinics, is a key driver. Furthermore, advancements in printing technology allow for vibrant, durable, and medically compliant designs, making these masks a more appealing choice for a wider consumer base. The value of this market is expected to reach approximately $20,000 million by 2033, indicating a robust and sustained upward trajectory. The market for printed medical masks is segmented by application into Hospitals, Clinics, and Everyday Public Places. While hospitals and clinics represent established markets, the rapid growth in "Everyday Public Places" signifies a shift in consumer behavior towards proactive health and safety. The types of masks include General Medical Masks and Medical Surgical Masks, with printed designs increasingly being incorporated into both. Key market restraints include stringent regulatory approvals for medical devices, which can slow down the introduction of new products, and the potential for higher manufacturing costs associated with printing compared to standard masks. However, the growing influence of social media trends and the desire for self-expression are creating unique opportunities. Companies like Dr. Talbot's, Maskita, and Ju Color are actively innovating, offering a diverse range of designs that cater to both functional needs and aesthetic preferences, thereby shaping the future of this dynamic market.

The Disposable Face Mask Market Report is Segmented by Product Type (Non-Woven, Protective, Surgical, Dust, Others), Application (Industrial Use, Personal Use), Distribution Channel (Offline, Online), and Geography (North America, Europe, Asia-Pacific, Middle East and Africa, South America). The Market Forecasts are Provided in Terms of Value (USD).

Masks are one of the few preventative measures that can be taken against COVID-19 in the absence of immunization, so it is imperative that people wear them whenever they are in an environment where they may be exposed to respiratory infections. Using this dataset, it is possible to develop a model that can differentiate between individuals who are wearing masks and individuals who are not wearing masks. This dataset contains a total of 20,347 images belonging to the 2 classes.