• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.8
• /
• pp.395-400
• /
• 2020

Coronavirus disease 2019 (COVID-19) was identified in December 2019 in China and has spread globally, resulting in an ongoing pandemic. Because COVID-19 is spread mainly from person to person, every person is required to wear a facemask in public. On the other hand, many people are still not wearing facemasks despite official advice. This paper proposes a method to predict whether a human subject is wearing a facemask or not. In the proposed method, two eye regions are detected, and the mask region (i.e., face regions below two eyes) is predicted and extracted based on the two eye locations. For more accurate extraction of the mask region, the facial region was aligned by rotating it such that the line connecting the two eye centers was horizontal. The mask region extracted from the aligned face was fed into a convolutional neural network (CNN), producing the classification result (with or without a mask). The experimental result on 186 test images showed that the proposed method achieves a very high accuracy of 98.4%.

• Biomedical Science Letters
• /
• v.28 no.4
• /
• pp.317-321
• /
• 2022

Due to COVID-19 pandemic, wearing face masks is obligatory to prevent respiratory virus transmissions in the community. However, there are few studies of the desirable number of wearing a face mask, and how to store them for reuse. Therefore, in this study, a survey was conducted among 208 healthy adults, and 27 kf-94 masks worn for 1, 2, and 3 days were collected. To estimate the risk of bacterial contamination, we analyzed the extent of bacterial contamination of the BHI medium and 16S rRNA gene sequencing. With an increase in the number of days of using the mask, the degree of bacterial contamination of the used mask gradually increased. As a result of 16S rRNA PCR performed for strain identification, Staphylococcus, known as a pathogenic bacterium, was identified the most. In conclusion, we found that wearing a cotton KF mask provides an optimal environment for microbes, which are related to the skin and respiratory system, to thrive. Therefore, it is also important to reduce the risk of bacterial infection of the face mask with appropriate sterilization methods.

• Journal of Broadcast Engineering
• /
• v.27 no.5
• /
• pp.619-628
• /
• 2022

Although face recognition and face generation have been growing in popularity, the privacy issues of using facial images in the wild have been a concurrent topic. In this paper, we propose a face editing network that can reduce privacy issues by generating face images with various properties from a small number of real face images and facial mask information. Unlike the existing methods of learning face attributes using a lot of real face images, the proposed method generates new facial images using a facial segmentation mask and texture images from five parts as styles. The images are then trained with our network to learn the styles and locations of each reference image. Once the proposed framework is trained, we can generate various face images using only a small number of real face images and segmentation information. In our extensive experiments, we show that the proposed method can not only generate new faces, but also localize facial attribute editing, despite using very few real face images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2547-2567
• /
• 2021

It has been widely acknowledged that occlusion impairments adversely distress many face recognition algorithms' performance. Therefore, it is crucial to solving the problem of face image occlusion in face recognition. To solve the image occlusion problem in face recognition, this paper aims to automatically de-occlude the human face majority or discriminative regions to improve face recognition performance. To achieve this, we decompose the generative process into two key stages and employ a separate generative adversarial network (GAN)-based network in both stages. The first stage generates an initial coarse face image without an occlusion mask. The second stage refines the result from the first stage by forcing it closer to real face images or ground truth. To increase the performance and minimize the artifacts in the generated result, a new refine loss (e.g., reconstruction loss, perceptual loss, and adversarial loss) is used to determine all differences between the generated de-occluded face image and ground truth. Furthermore, we build occluded face images and corresponding occlusion-free face images dataset. We trained our model on this new dataset and later tested it on real-world face images. The experiment results (qualitative and quantitative) and the comparative study confirm the robustness and effectiveness of the proposed work in removing challenging occlusion masks with various structures, sizes, shapes, types, and positions.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.23 no.3
• /
• pp.615-623
• /
• 1996

Face mask is an extraoral appliance which used to protract maxilla, and can help in the correction of moderately severe class IlI malocclusions by the anterior displacement of the maxilla and maxillary dentition, and possibly restricting or changing the direction of the growth of the mandible. In three cases the results were followed. 1. Anterior crossbite was corrected 2. Maxilla & maxillary dentition were displaced forwardly. 3. Lingual tipping of the mandibular incisors, and backward & downward rotation of mandible were performed. 4. Acceptable improvement in the class III profile was performed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.3
• /
• pp.490-493
• /
• 2021

This paper proposes an embedded system that detects mask and face recognition based on a microprocessor instead of Nvidia Jetson Board what is popular development kit. We use a class of efficient models called Mobilenets for mobile and embedded vision applications. MobileNets are based on a streamlined architechture that uses depthwise separable convolutions to build light weight deep neural networks. The device used a Maix development board with CNN hardware acceleration function, and the training model used MobileNet_V2 based SSD(Single Shot Multibox Detector) optimized for mobile devices. To make training model, 7553 face data from Kaggle are used. As a result of test dataset, the AUC (Area Under The Curve) value is as high as 0.98.

• Archives of Craniofacial Surgery
• /
• v.24 no.2
• /
• pp.66-72
• /
• 2023

Background: During the coronavirus disease 2019 (COVID-19) pandemic, the everyday use of face masks massively increased to prevent the spread of infection. Many people complain of ear pain and erosion when wearing a mask for extended periods of time. If prolonged mask usage is uncomfortable for ordinary people, a question arises-how much more inconvenient must mask wearing be for patients with a full-thickness skin graft (FTSG) donor site in the retroauricular region? Herein, we evaluated complications related to face mask use in 27 patients with a retroauricular FTSG donor site, with the goal of clarifying whether the retroauricular region is still an appropriate FTSG donor site in the context of the COVID-19 pandemic. Methods: Complications in 27 patients treated by FTSGs harvested from the retroauricular region from 2019 to 2021 were investigated. A questionnaire comparing the normal and the operated sides was administered. Pain, itching, soreness, deformity, and symmetry were further investigated. Results: Pain and itching were the only observed complications. The operated side was slightly more painful than the normal side in four patients (14.8%), and four patients (14.8%) reported itching on the operated side. However, all patients who experienced complications stated that the pain or itching did not interfere with mask wearing. Most symptomatic patients were older than 60 years of age (23.8%, p= 0.185) and wore masks for longer periods of time (28.5%, p= 0.326). Conclusion: Few retroauricular donor site-related complications occurred, and none of these complications caused inconvenience in daily life. Therefore, in the COVID-19 pandemic, the use of the retroauricular region as an FTSG donor site remains appropriate.

• Convergence Security Journal
• /
• v.22 no.2
• /
• pp.21-26
• /
• 2022

Wearing face masks is an effective measure to prevent COVID-19 infection. Infrared thermal image based temperature measurement and identity recognition system has been widely used in many large enterprises and universities in China, so it is totally necessary to research the face mask detection of thermal infrared imaging. Recently introduced MTCNN (Multi-task Cascaded Convolutional Networks)presents a conceptually simple, flexible, general framework for instance segmentation of objects. In this paper, we propose an algorithm for efficiently searching objects of images, while creating a segmentation of heat generation part for an instance which is a heating element in a heat sensed image acquired from a thermal infrared camera. This method called a mask MTCNN is an algorithm that extends MTCNN by adding a branch for predicting an object mask in parallel with an existing branch for recognition of a bounding box. It is easy to generalize the R-CNN to other tasks. In this paper, we proposed an infrared image detection algorithm based on R-CNN and detect heating elements which can not be distinguished by RGB images.

• Archives of Craniofacial Surgery
• /
• v.18 no.4
• /
• pp.223-229
• /
• 2017

The beauty of the laryngeal mask is that it forms an air tight seal enclosing the larynx rather than plugging the pharynx, and avoid airway obstruction in the oropharynx. The goal of its development was to create an intermediate form of airway management face mask and endotracheal tube. Indication for its use includes any procedure that would normally involve the use of a face mask. The laryngeal mask airway was designed as a new concept in airway management and has been gaining a firm position in anesthetic practice. Despite wide spread use the definitive role of the laryngeal mask airway is yet to be established. In some situations, such as after failed tracheal intubation or in oral surgery its use is controversial. There are several unresolved issues, for example the effect of the laryngeal mask on regurgitation and whether or not cricoids pressure prevents placement of mask. We review the techniques of insertion, details of misplacement, and complications associated with use of the laryngeal mask. We then attempt to clarify the role of laryngeal mask in air way management during anesthesia, discussing the advantages and disadvantages as well as indications and contraindications of its use in oral and maxillofacial surgery.

• Journal of Korean Society for Quality Management
• /
• v.46 no.2
• /
• pp.301-310
• /
• 2018

Purpose: The purpose of this study is to investigate the effect of work intensity on fit factor and affective quality of the dustproof Background: Among the victims who suffer pneumoconiosis due to the inhalation of toxic substances or the lack of oxygen during the work, the proportion of the victims is larger than the other causes. Wearing a respirator may prevent pneumoconiosis, but it can be hazardous to workers because of the leakage through filters, cartridges, exhaust valves, broken parts, and face-to-face contact. Despite leakage through the contact area between the mask and the face has various causes such as the wearer's activity, sweat accumulation, facial shape, etc., There is a lack of relevant research and regulation compared to developed countries that have already institutionalized the law 30 years ago and give the right to sell through a test Method: The work intensity was adjusted by walking or running at 6km/h and 11km/h on the treadmill, and tasks were defined with reference to the test procedure and the exercise sequence applied in the face leakage test of the dustproof mask. And fit factor was measured objectively using 'Respirator Fit Tester 8038' which measures fit factor calculated by dividing the number of dust present outside the mask by inside the mask. In addition, affective quality was classified by the ease of use, ease of breathing, and ease of wearing, and was measured using the 5-point likert scale questionnaire. Results: There was a significant difference in fit factor, ease of breathing, and wearing convenience according to work intensity and no significant difference in ease of use(${\alpha}=0.01$). And when the work intensity was high, fit factor, ease of breathing, and wearing convenience were all lower than when the work intensity was low. Conclusion: In Korea, it is necessary to consider consideration of the work intensity when testing the leakage rate of the face part for safety certification of the respiratory protective equipment, When developing a mask, it should be possible to maintain high adhesion even under intense, active situation and high temperature conditions by selecting materials, improving the wearing style, and expanding the adjustable range.