Face mask wearing image dataset: A comprehensive benchmark for image-based face mask detection models

Globally, the use of face masks is one of the non-pharmaceutical interventions recommended as a method of preventing spread of SARS-CoV-2. Lagos State was an epicenter of COVID-19 and as such, the State Government made the use of facemasks mandatory while in the public and social gatherings. Due to the alarming rate of spread of COVID-19 pandemic, shortage of masks and respirators has been observed and reported globally. This has led to production and use of different types of facemasks including locally made facemasks of different fabrics. A total of 400 consisting of 200 made of local fabrics, 100 imported face/surgical masks and 100 N95 respirators were selected from different sources in Lagos State between May 2020 and November 2020. Samples were immersed aseptically into conical flask containing 100ml Nutrient broth and incubated 18-24hrs. The broth culture was sub-cultured onto Sabouroid Dextrose Agar in duplicates. One of the SDA was incubated at room temperature and the other at 37°C. Blood, Chocolate and MacConkey agar plates were also inoculated and incubated at 37°C for 18-24 hrs. Isolates were identified using phenotypic identification methods. Of the total 400 samples, 346 (86.5%) had no bacterial or fungal growth while 44 (11.0%) had one bacterial isolate and 10 (2.5%) had mixed growth of bacterial isolates. Of the 200 locally-made face masks, 39 (19.5%) had one bacterial isolate and 9 (4.5%) had two bacterial isolates and 5 (2.5%) had fungal isolates while out of the 100 imported surgical masks, only 4 (4.0%) had one bacterial isolate and one (1.0%) had mixed growth of bacterial isolates. One (1.0%) of the imported N95 respirator had only one bacterial isolate <i>(Lactobacilli spp)</i>. Generally, the isolated bacteria were <i>Staphylococcus aureus, Coagulase negative Staphylococcus, Escherichia coli, Klebsiella species and Lactobacilli species while fungal isolates were Candida albicans and Aspergillus fumigatus</i>. The locally-made face masks were contaminated with both bacterial and fungal isolates. Face masks with no bacterial or fungal growth had a p-value of 0.02 and it is statistically significant in terms of the face masks tested in this study. Face masks with one bacterial isolate had a p value of 0.35 and those mixed growth of two different bacterial and fungal isolates had a p value of 0.36 which indicated a non-statistically significant results of the face mask tested in these categories. Locally made face masks were more contaminated with single or mixed bacterial and fungal agents. Cautionary use of the masks is recommended.

During the COVID-19 pandemic, the protective face mask has proven to be essential. The protective face masks cover the lower part of the face, including teeth and, for orthodontic patients, the orthodontic appliances. The aim of this study was to assess the impact that the restrictive measures that were imposed during the COVID-19 pandemic and, especially, wearing a protective face mask had on a sample of Romanian children, and to compare the results previously obtained on a sample of Romanian teenagers with the results obtained after investigating children under the age of 12 years. The cross-sectional survey was conducted in two orthodontic offices from the city of Oradea, Romania. The study sample included children with ages between 8 and 11.9 years that were undergoing an orthodontic treatment with removable or fixed orthodontic appliances. After obtaining the results, comparisons were made with the answers provided by a group of adolescents previously investigated. The questionnaires consisted of 9 items that investigated children’ attitudes toward protective face mask wearing and other aspects related to the COVID-19 pandemic. Two hundred fifty-six children were included in the study (53.1% female patients, 46.9% male patients). Most of the children were not worried that face masks would hide their orthodontic appliances (Item 1—Never, 40.2%; Rarely, 28.9%) and did not consider that the necessity of face mask wearing negatively impacted their desire to undergo an orthodontic treatment, despite the fact that it covered the appliances (Item 2—Never, 37.1%; Rarely, 31.6%). However, 44.5% of children were not happy because they had to wear a face mask during the orthodontic treatment, considering the fact that it covered the orthodontic appliance (Item 6), and most patients (49.2%) did not want the face mask to continue to be mandatory (Item 7). Although children were not happy that they had to wear a face mask that covered the orthodontic appliances, protective face masks were generally well tolerated by Romanian children.

In this paper, we investigate the problem of face mask compliance classification in response to the Corona Virus Disease (COVID-19) pandemic. Since the start of the pandemic, many governments and businesses have been continually updating policies to help slow the spread of the virus, including requiring face masks to use many public and private services. In response to these policies, many researchers have developed new face detection and recognition techniques for masked faces. Many of the developed approaches proposed to address the problem of masked face detection have been relatively successful. However, these approaches almost exclusively focus on detecting the presence or absence of someone wearing a face mask. It is understood and broadly discussed in various reports and the media that there are people not always following the suggested guidelines provided by public health authorities for wearing face masks, which include ensuring the face mask properly covers the nose and mouth. To date, very few research publications exist that investigate the capability of modern classification algorithms to efficiently distinguish between masked faces in the visible band that are either compliant or non-compliant with the suggested guidelines. Furthermore, to the best of our knowledge, there is no publication in the open literature that focuses on the investigation of face mask classification in the thermal band. As thermal sensors continue to improve in quality and decrease in cost, surveillance applications using thermal imagery are expected to continue to grow and benefit those organizations considering the automation of face mask detection and compliance. In this study, we propose an investigation on face mask compliance in both the thermal and visible bands. It is composed of the following salient steps; (1) the creation of a multi-spectral masked face database from subjects wearing or not wearing face masks, (2) the augmentation of the generated database with synthetic face masks to simulate two different levels of non-compliant wearing of face masks, and (3) the assessment of a variety of CNN architectures on the previous augmented database to investigate any differences between classifying thermal and visible masked faces. Experimental results show that face mask compliance classification in both studied bands yield a classification accuracy that reaches 100% for most models studied, when experimenting on frontal face images captured at short distances with adequate illumination.KeywordsFace masksCOVID-19PandemicFace mask classificationDeep learningMask complianceThermal imagingMulti-spectral Imaging

Environmental risks of disposable face masks during the pandemic of COVID-19: Challenges and management

&#x0D; &#x0D; &#x0D; The COVID-19 pandemic in early 2020 has created a health crisis around the world. There have been many precautions taken against the virus, such as social distancing and the use of personal protective equipment. Face masks are an essential part of personal protective equipment, especially for essential workers. Although the pandemic has caused a high demand for facemasks, there is limited scientific knowledge available on the various types of masks. Knowledge about the air quality inside the different facemasks could be beneficial for both the COVID-19 pandemic and future disease outbreaks, which will seemingly increase in the future. There are different types of masks, ranging from tight-fitting N95 respirator masks to looser surgical masks to homemade cloth masks. Herein, N95 respirator masks, surgical masks, cloth face masks, and surgical masks on top of N95 respirator masks were compared in terms of CO2 levels, Volatile Organic Compound levels (VOCs), temperature, humidity, and O2 concentrations. To record these measurements, Arduino-based sensors were constructed and utilized for the measurements. It was found that the N95 mask and the surgical mask on top of the N95 mask trapped the highest concentration of carbon dioxide, VOCs, temperature, humidity, and the lowest oxygen levels compared to the surgical mask and cloth mask.&#x0D; &#x0D; &#x0D;

Face masks used during the COVID-19 pandemic are composed of polymers which when broken down release microplastics to the environment. As part of the most extensive monitoring program of COVID face mask littering ever undertaken for a coastal community, 50 parking lots in the town of Truro, Nova Scotia were surveyed for half a year (November 2021-April 2022). A total of 3,036 discarded or lost face masks were retrieved, with abandonment being consistent through time but for the notable exception of a period of rapid melting that released masks which had been damaged by snow removal maintenance. Qualitative observations and mark-and-recapture experiments indicated parking lots to be sources of litter dispersed to the wider environment. Interpolating these data on loss rates suggests that each of the 25,583 residents of Truro are estimated to have abandoned five face masks in parking lots during the 20 months of the peak pandemic. Expanding these results to the population of a quarter of a million people living around the Bay of Fundy, and using the known material composition of face masks, produces an estimate of 2,822 kg of pandemic plastic waste being generated with the potential to decompose and release microplastics over subsequent years into the Bay of Fundy, a designated World Heritage Site.

BackgroundThe World Health Organization issued guidelines for face mask use in community settings during the current COVID-19 pandemic. However, data are limited on public compliance with those guidelines in Sudan. Therefore, this study assessed face mask-wearing practice and technique during the COVID-19 pandemic among residents of Sudan.MethodsA cross-sectional study was conducted from July to September 2021 among Sudanese aged ≥18 years. A web-based questionnaire was shared through different social media platforms. Personal characteristics, four knowledge-associated items, three attitude-associated items, one item concerning mask-wearing practice, and five items related to mask-wearing technique were determined. Univariate, bivariate, and multivariable analyses were performed using STATA v17.ResultsThe survey included 1059 participants (48% males, 52% females) from different regions of Sudan. The overall mean ± SD was 3 ± 0.73 for knowledge of COVID-19 transmission; 2.3 ± 0.71 for attitude toward wearing face masks; 0.38 ± 0.49 for the practice of wearing a face mask; and 4.17 ± 0.97 for face mask-wearing technique. Approximately one-third (38%) of participants always wore a face mask during the pandemic, with age, sex, education level, family income, face mask attitude, occupation, and history of COVID-19 infection affecting the practice. All steps of face mask-wearing technique were performed by 46% of participants (59% performed hand hygiene before putting on a mask and 86% after removing it; 98% covered mouth and nose; 90% adjusted masks at the nose bridge, and 84% tied masks securely), and associated with age, occupation, family income, history of COVID-19 infection, and face-mask attitude.ConclusionAlthough knowledge and attitude were relatively good, the practice of wearing a face mask and using proper techniques among participants were low. To ensure optimal face mask use and proper mask-wearing techniques, educational intervention and establishing governmental regulations are highly recommended.

Since face masks may help slow the spread of diseases, a patient may wear a face mask for an MRI exam during the COVID-19 pandemic. However, metal parts, like nose or face clips within the mask, may burn the patient during an MRI. In this numerical study, we investigated the two-channel RF shimming effect on the RF-induced local SAR of a face mask with a metal strip. With the parallel transmission RF field exposure to the virtual adult male model with a face mask, the RF-induced local SAR <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1g</inf> is calculated for each excitation condition. Under the exposure limit of a whole-body averaged SAR of 2 W/kg and head averaged SAR of 3.2 W/kg, the peak SAR <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1g</inf> is 178 W/kg and 62 W/kg occurs at the nose touching the metal strip. The SAR <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1g</inf> value is higher on the skin area close to the metal strip than at other locations. The metal strip within the face mask could cause a potential RF-induced heating hazard.

Airborne transmission of respiratory viruses consists of three sequential steps: (1) release of respiratory fluids in the form of droplets from the nose and mouth of an infected person, (2) transport of the droplets through air, and (3) entry of the droplets into the nose and mouth of an uninfected individual. Talking, coughing, and sneezing emit droplets across a spectrum of sizes. The water in exhaled droplets begins to evaporate in air and, as a result, the droplets are reduced in size shortly after being emitted. Face masks are effective for capturing droplets just released from the nose and mouth. Studies indicate that more than 50% of community transmission of SARS-CoV-2 is from asymptomatic and pre-symptomatic cases. Use of face masks by the public can effectively reduce the chance of infected individuals unknowingly spreading the virus. In addition to being an effective device for source control, face masks can protect the wearers from inhaling virus-laden droplets. Cloth masks and disposable masks provide reasonable protection for the public, while surgical masks and N95 respirators give higher levels of protection as needed in healthcare settings. Made with varied materials, these masks have different structural characteristics. The collection efficiency of a face mask depends on droplet size, face velocity, and the structural characteristics of the mask. For a given mask, capturing droplets is more effective during exhalation than during inhalation. Pressure drop across the mask should be taken into consideration when selecting a face mask. The best face mask is the one that gives the highest collection efficiency with the least pressure drop. For an effective protection, a mask should fit the face properly. While face masks have proven adequate in reducing airborne transmission of SARS-CoV-2 infections, continuous improvement is needed to better prepare for future respiratory viral threats.

Face masks have been associated with effective prevention of diffusion of viruses via droplets. However, the use of face masks among children, especially those aged younger than 3 years, is debated, and the US Centers for Disease Control and American Academy of Physicians recommend the use of face mask only among individuals aged 3 years or older. To examine whether the use of surgical facial masks among children is associated with episodes of oxygen desaturation or respiratory distress. This cohort study was conducted from May through June 2020 in a secondary-level hospital pediatric unit in Italy. Included participants were 47 healthy children divided by age (ie, group A, aged ≤24 months, and group B, aged >24 months to ≤144 months). Data were analyzed from May through June 2020. All participants were monitored every 15 minutes for changes in respiratory parameters for the first 30 minutes while not wearing a surgical face mask and for the next 30 minutes while wearing a face mask. Children aged 24 months and older then participated in a walking test for 12 minutes. Changes in respiratory parameters during the use of surgical masks were evaluated. Among 47 children, 22 children (46.8%) were aged 24 months or younger (ie, group A), with 11 boys (50.0%) and median (interquartile range [IQR]) age 12.5 (10.0-17.5) months, and 25 children (53.2%) were aged older than 24 months to 144 months or younger, with 13 boys (52.0%) and median (IQR) age 100.0 (72.0-120.0) months. During the first 60 minutes of evaluation in the 2 groups, there was no significant change in group A in median (IQR) partial pressure of end-tidal carbon dioxide (Petco2; 33.0 [32.0-34.0] mm Hg; P for Kruskal Wallis = .59), oxygen saturation (Sao2; 98.0% [97.0%-99.0%]; P for Kruskal Wallis = .61), pulse rate (PR; 130.0 [115.0-140.0] pulsations/min; P for Kruskal Wallis = .99), or respiratory rate (RR; 30.0 [28.0-33.0] breaths/min; P for Kruskal Wallis = .69) or for group B in median (IQR) Petco2 (36.0 [34.0-38.0] mm Hg; P for Kruskal Wallis = .97), Sao2 (98.0% [97.0%-98.0%]; P for Kruskal Wallis = .52), PR (96.0 [84.0-104.5] pulsations/min; P for Kruskal Wallis test = .48), or RR (22.0 [20.0-25.0] breaths/min; P for Kruskal Wallis = .55). After the group B walking test, compared with before the walking test, there was a significant increase in median (IQR) PR (96.0 [84.0-104.5] pulsations/min vs 105.0 [100.0-115.0] pulsations/min; P < .02) and RR (22.0 [20.0-25.0] breaths/min vs 26.0 [24.0-29.0] breaths/min; P < .05). This cohort study among infants and young children in Italy found that the use of facial masks was not associated with significant changes in Sao2 or Petco2, including among children aged 24 months and younger.

The airborne diffusion of saliva droplets during respiratory activities is one of the major factors in the spread of infections. During the COVID-19 pandemic, the use of protective face masks was essential to reduce the risk of infection and spread of SARS-CoV-2. The face mask is able to significantly reduce the saliva droplet emission in front of the person. However, the use of masks also produces a particle leakage towards the back of the person, which could increase the infection risk of people behind the subject. Most of the experimental investigations applied invasive and/or complex experimental techniques to evaluate the face masks leakage. The primary objective of this study is to develop a novel, non-invasive methodology for assessing rearward droplet emission associated with the use of protective face masks. Specifically, a thermographic analysis of the thermal footprint released during ordinary and extraordinary respiratory activities is presented, evaluating the maximum temperature, the detection time, and the spread area of the thermal footprint. Both surgical and FFP2 face masks were tested. Two different subjects were involved in the experimentation to evaluate the influence of face conformation. The findings indicate that the area influenced by droplet dispersion is larger when wearing a surgical mask compared to an FFP2 mask, with the highest recorded temperatures observed for the surgical mask. The thermal footprint was found to be strongly dependent on individual facial morphology and mask fit. Notably, the FFP2 mask also altered the position of the thermal footprint, which was primarily confined to the region near the neck.

Nowadays, effective measures are needed to reduce the harm caused by electromagnetic pollution and microplastic (MP) pollution in a water environment. Besides, since the COVID-19 pandemic in 2019, people have made a lot of progress in the recycling of waste face mask (FM) pollution. However, so far, no publications are available in the literature that simultaneously solve the problem of MP pollution, electromagnetic pollution, and FM pollution. Herein, FMs, polyethylene MPs (PE MPs), and carbon nanotubes (CNTs) were used to fabricate EMI shielding composites with an isolated conductive network structure via the adhesion ability of polydopamine (PDA). The effects of isolated conductive networks, different sizes of PE MPs, and different layers of FMs on the adsorption behavior of FMs–PDA–CNT, as well as electrical performance for the obtained PP–PDA–CNT composites, were studied. The composites displayed the EMI SE for 25.9 dB in the X-band with a 3 wt % CNT content due to the isolated conductive network structure, which may be useful to the simultaneous elimination of garbage from the electromagnetic pollution, FM pollution, and MP pollution to a certain degree.

The COVID-19 pandemic has exacerbated the problem of environmental contamination of disposable personal protective equipment, in particular face masks (FMs). As a result of environmental factors, FMs undergo aging and fragmentation processes and become a source of microplastics (MPs) and chemical additives. Taking into account the scale of accumulation of used FMs and their fragments in the coastal zone, it should be expected that the most appreciable ecotoxicological consequences should be observed in hydrobionts inhabiting coastal ecosystems. Based on this, the aim of this study was to investigate the toxicity of leachates from pristine and weathered FMs using sperm of sand dollars Scaphechinus mirabilis. In our work, we used pristine and weathered FMs, which for 200 days were kept in the external environment under natural conditions and exposed to a complex of climatic factors. Fourier transform infrared spectroscopy was used to characterize the chemical changes that occurred in the polymer structure of FMs during this period. It follows from the results obtained that leachates from pristine and weathered FMs reduced sperm viability; stimulated the accumulation of lipid peroxidation products, such as malondialdehyde (MDA); and significantly increased the destruction of DNA molecules, showing a genotoxic effect. Overall, our results complement the limited experimental data presented, indicating the genotoxic properties of face mask extracts.

Alongside the use of face mask as a preventive measure during the COVID-19 pandemic, it has been noticed a high increase in chalazion incidence. Purpose: To determine whether or not using face mask is correlated to the rise in chalazion cases among patients. Material and Methods: This is a retrospective multicentric study, conducted in two different hospitals distanced by more than 500 Km (Rabat Military Hospital and Tetouan’s Provincial Hospital). Records of the operative rooms and medical visits of both centers were reviewed and patients with chalazion were included. We, then, determined the incidence of chalazion for each month between March and September of years 2018, 2019, 2020, 2021, and 2022. The data collected was then processed by the software Jamovi 22.0. Results: It is clear through our data analyses that the chalazion incidence rose in the pandemic period compared to the same month of the years 2018, 2021 and 2022. The risk of developing chalazia also increased with the frequent use of face mask daily. Conclusion: face mask wear appears to have a direct link to chalazion formation. To keep a safe balance between the protective role of face mask and its adverse effect on the ocular surface stability, many measure may be proposed and appear to be quite efficient.

ObjectivesThe aim of the study was to evaluate self-reported MADE during the COVID-19 pandemic in dental healthcare practitioners and identify their possible risk factors.Material and MethodsAn anonymous questionnaire was sent to doctors of dental medicine in the time period from February 2022 to August 2022. The online questionnaire included demographic characteristics and clinical characteristics: presence and deterioration of DED symptoms while wearing the face mask, personal protective face equipment, use of contact lenses, history of eye surgery, current use of medications, number of hours wearing face mask, and evaluation of subjective DED symptoms using modified Ocular Surface Disease Index (OSDI).ResultsA total of 405 participants were included in the study and an overall prevalence of MADE was 29.1% (95% CI: 24.7 - 33.6). The participants who used masks more than 6 hours per day during the whole day reported a higher OSDI score (12.5 (IQR = 2.6 – 29.2)) compared to the participants who used masks less than 6 hours/day (6.25 (IQR = 0 – 22.92); Mann-Whitney U Test p = 0.066). Multivariable logistic regression revealed the following possible risk factors for self-reported MADE: age (older than 61 years) OR: 3.522 (95% CI 1.448 - 8.563); p=0.05, and wearing the face mask more than 6 h at work OR: 1.779 (95% CI 1.017 – 3.113); p=0.044.ConclusionThe prevalence of self-reported MADE among dental healthcare practitioners appears to be significant. The use of a face mask for a prolonged duration increases OSDI scores. MeSH Terms: face masks, dry eye, MADE, ocular discomfort, COVID-19, protective face equipment