A Mask Detection Algorithm Based on Improved Yolov5s

Aiming at the severe form of new coronavirus epidemic prevention and control, a target detection algorithm is proposed to detect whether masks are worn in public places. The Ghostnet and SElayer modules with fewer design parameters replace the BottleneckCSP part in the original Yolov5s network, which reduces the computational complexity of the model and improves the detection accuracy. The bounding box regression loss function DIOU is optimized, the DGIOU loss function is used for bounding box regression, and the center coordinate distance between the two bounding boxes is considered to achieve a better convergence effect. In the feature pyramid, the depthwise separable convolution DW is used to replace the ordinary convolution, which further reduces the amount of parameters and reduces the loss of feature information caused by multiple convolutions. The experimental results show that compared with the yolov5s algorithm, the proposed method improves the mAP by 4.6% and the detection rate by 10.7 frame/s in the mask wearing detection. Compared with other mainstream algorithms, the improved yolov5s algorithm has better generalization ability and practicability. © 2022 ACM.

Improved mask detection based on YOLOv5s

COVID-19 epidemic is not over. The correct wearing of masks can effectively prevent the spread of the virus. Aiming at a series of problems of existing mask-wearing detection algorithms, such as only detecting whether to wear or not, being unable to detect whether to wear correctly, difficulty in detecting small targets in dense scenes, and low detection accuracy, It is suggested to use a better algorithm based on YOLOv5s. It improves the generalization and transmission performance of the model by changing the ACON activation function. Then Bifpn is used to replace PAN to effectively integrate the target features of different sizes extracted by the network. Finally, To enable the network to pay attention to a wide area, CA is introduced to the backbone. This embeds the location information into the channel attention. © 2023 SPIE.

Face Mask detection using Mask R-CNN to control the spread of Covid-19

Business executives are developing cutting-edge digital solutions as the virus outbreak spreads. A face mask detection system is one of them, and it can be used to spot people wearing them. Face mask identification software and applications have already been released by a few businesses, and others have promised to do the same for the service. The proposed work examines face mask detection accuracy using CNN networks. Mask wear is now required in many developed and developing countries worldwide when leaving the house or entering public spaces. It will be difficult to maintain touchless access control in buildings while recognising faces wearing masks on any surveillance systems. Masks covering faces has made face detection algorithms and performance difficult. The proposed work detect face mask labeled no mask or mask with detection accuracy. The work train the system to click images of a face and provide labeled data. The work is classified using Convolution Neural Network (CNN), a Deep learning technique, to classify the input image with the help of the classification algorithm MobileNetV2. The trained system shows whether a person in the video frame is wearing a mask or not. © 2023 IEEE.

Detection of Real Time Face Mask using Convolutional Neural Network

In recent years, the global pandemic like COVID - 19 has changed the lifestyle of people. Wearing face mask is must in order to stay safe and healthy. This paper presents a real-time face mask detector which identifies whether a human is wearing a mask or not. Moreover, this system can also recognize the person wearing a face mask inappropriately or wear other things except a face mask. The proposed algorithm for face mask detection in this system utilizes Haar cascade classifier to detect the face and Convolutional Neural Networks to detect the mask. The whole system has been demonstrated in a practical application for checking people wearing face mask. © 2023 IEEE.

COVID bell - A smart doorbell solution for prevention of COVID-19

The article introduces a novel strategy for efficiently mitigating COVID-19 distribution at the local level due to contact with any surfaces. Our project aims to be a critical safety shield for the general people in the fight against the epidemic. An ultrasonic sensor is integrated with the automated doorbell system to ring the doorbell with a hand motion. A temperature sensor Mlx90614 is also included in the system, which records the temperature of the person standing in front of the door. The device also includes a camera module that captures the image of the person standing at the front entrance. The captured image is processed through an ML model which runs at over 30 fps to detect whether or not the person is wearing a mask. The image and the temperature of the person standing outside are sent to the owner through the configured iOS application. If the person outside is wearing a mask, one can open the door through the app itself and permit the entry of the person standing outside thereby integrating the edge device with an app for a better user experience. The system helps in reducing physical contact, and the results obtained are at par with the already existing solutions and provide a few advantages over them. © 2023 the author(s), published by De Gruyter.

Masked Face Recognition Using Multi-Task Cascaded Convolutional Networks and FaceNet

Face masks have been widely used since the start of the COVID-19 pandemic. Facial detection and recognition technologies, such as the iPhone's Face ID, heavily rely on seeing the facial features that are now obscured due to wearing a face mask. Currently, the only way to utilize Face ID with a mask on is by having an Apple Watch as well. As such, this paper intends to find initial means of a reliable personal facial recognition system while the user is wearing a face mask without having the need for an Apple Watch. This may also be applicable to other security systems or measures. Through the use of Multi-Task Cascaded Convolutional Networks or MTCNN, a type of neural network which identifies faces and facial landmarks, and FaceNet, a deep neural network utilized for deriving features from a picture of a face, the masked face of the user could be identified and more importantly be recognized. Utilizing MTCNN, detecting the masked faces and automatically cropping them from the raw images are done. The learning phase then takes place wherein the exposed facial features are given emphasis while the masks themselves are excluded as a factor in recognition. Data in the form of images are acquired from taking multiple pictures of a certain individual's face as well as from repositories online for other people's faces. Images used are taken in various settings or modes such as different lighting levels, facial angles, head angles, colors and designs of face masks, and the presence or absence of glasses. The goal is to recognize whether it is the certain individual or not in the image. The training accuracy is 99.966% while the test accuracy is 99.921%. © 2022 IEEE.

YOLOv7 for Face Mask Identification Based on Deep Learning

The World Health Organization (WHO) has publicized a global public health emergency due to the COVID-19 coronavirus pandemic. Wearing a mask in public can provide protection against the spread of disease. Tremendous progress has been made in object detection in recent times, thanks in large part to deep learning models, which have shown encouraging results when it comes to recognizing objects in images. Recent technological developments have made this progress possible. Wearing a mask in public is one way to prevent the transmission of COVID-19 from others. Our study employs You Only Look Once (YOLO) v7 to determine whether a subject is wearing a mask, and then divides them into three groups depending on the degree to which they are wearing a mask correctly (none, bad, and good). In this study, we merged two datasets, the Face Mask Dataset (FMD) and the Medical Mask Dataset (MMD), to conduct our experiment. These models' evaluations and ratings include crucial criteria. According to our data, YOLOv7 achieves the highest mAP (98.5%) in the "Good"class. © 2023 IEEE.

Comparing COVID spread to mask-wearing rates in public transportation using AI detection

The spread of COVID-19 has resulted in several changes worldwide. In particular, border closures and economic stagnation have significantly affected societies. Although the implementation of preventive measures has improved the pandemic scenario in several countries, the effectiveness of vaccines has decreased with the emergence of mutant viruses. With this background, the use of masks is considered the best method for preventing the spread of the virus. Notably, public transportation is closely related to socioeconomic activities, and the spread of infectious diseases is more likely in closed, dense, and congested areas. Moreover, the probability of infection during public transportation also depends on the proportion of commuters wearing masks. Based on the closed-circuit television footage of various public transportation spaces, the number of mask wearers can be analysed using artificial intelligence deep learning, and the probability of COVID-19 spread can be predicted by determining the proportion of mask wearers among the commuters. With this background, in this study, the importance of masks in controlling the spread of the virus is confirmed. In conclusion, appropriate measures can be implemented by determining the probability of infection according to the mask-wearing rate in public transportation spaces. © 2023 ICE Publishing: All rights reserved.

In Real Time Face Mask Detection Alert System using CNN Model

Today's current scenario of the coronavirus pandemic (Covid19), where in the future there will be a need for efficient applications of real-time mask detection. Because, nowadays it is very difficult for doctors to handle patients infected with corona virus. Our major purpose of building a face-mask detection alert system using OpenCV that can detect individual person's if he/she is wearing a face mask or not wearing a face-mask using CCTV Camera, with quite a good accuracy. And also building and training the Convolutional Neural Network (CNN) using keras framework. After that, He / She refused to go to the locations or the regions wherever the officials were strictly asked to wear face-mask. After denying way in to the individual, the officers or the authorized person will receive an email in real time where the photograph of the person can be attached. In away screen panels could be installed at the entrances where the person's denied access can see a pop-up warning message. Where he/she would be advised to wear a face mask before getting access. This type of face mask detection alert system has some applications in schools, colleges, malls, theaters, offices and also other major crowded places or areas where it expects large public gathering. © 2022 IEEE.

Face Mask Classification based on Transfer Learning and MobileNet V2

Face mask image recognition can detect and monitor whether people wear the mask. Currently, the mask recognition model research mainly focuses on different mask detection systems. However, these methods have limited working datasets, do not give safety alerts, and do not work appropriately on masks. This paper aims to use the face mask recognition detection model in public places to monitor the people who do not wear the mask or the wrong mask to reduce the spread of Covid-19. The mask detection model supports transfer learning and image classification. Specifically, the collected data are first collected and then divided into two parts: with_mask and without_mask. Then authors build, implement the model, and obtain accurate mask recognition models. This paper uses and size of images datasets tested respectively. The experimental results show that the effect of the image size of was relatively better, and the training accuracy of different MobileNetV2 models is about 95%. Our analysis demonstrates that MobileNetV2 can correctly classify Covid-19. © 2022 ACM.

An Improved Computer Vision based Face Mask Detection and Alerting System

A global healthcare crisis has been declared as a result of the covid-19 nandemic's extensive snread. The coronavirus spreads mostly by the release of droplets from an infected person's irritated nose and throat. The risk of spreading disease is highest in public gathering places. Wearing a facial mask in public is one of the greatest ways, according to the World Health Organization, to avoid getting an infectious disease. This research work proposes an approach to human face mask detection using TensorFlow and OpenCV. Whether or not a character is wearing a mask is indicated by an enclosing field drawn around their head. An alert email will be sent to a person whose face is in the database if they make a call without a mask worn. © 2023 IEEE.

DenseNet201 Model for Robust Detection on Incorrect Use of Mask

In 2022, the COVID-19 pandemic is still occurring. One of the optimal prevention efforts is to wear a mask properly. Several previous studies have classified the use of masks incorrectly. However, the accuracy resulting from the classification process is not optimal. This research aims to use the transfer learning method to achieve optimal accuracy. In this research, we used three classes, namely without a mask, incorrect mask, and with a mask. The use of these three classes is expected to be more detailed in detecting violations of the use of masks on the face. The classification method used in this research uses transfer learning as feature extraction and Global Average Pooling and Dense layers as classification layers. The transfer learning models used in this research are MobileNetV2, InceptionV3, and DenseNet201. We evaluate the three models' accuracy and processing time when using video data. The experimental results show that the DenseNet201 model achieves an accuracy of 93%, but the processing time per video frame is 0.291 s. In contrast to the MobileNetV2 model, which produces an accuracy of 89% and the processing speed of each video frame is 0.106 s. This result is inversely proportional to accuracy and speed. The DenseNet201 model produces high accuracy but slow processing time, while the MobileNetV2 model is less accurate but has faster processing. This research can be applied in the crowd center to monitor health protocols in the use of masks in the hope of inhibiting the transmission of the COVID-19 virus. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Face mask detection based on improved YOLOv3 algorithm

In the current situation of COVID-19 prevention and control, wearing masks remains an important way to prevent the transmission of the Novel Coronavirus. Aiming at the problem that the detection accuracy of the traditional YOLOv3 algorithm can still be improved, this paper proposes an improved yolov3 algorithm and applies it to the practical problem of detecting whether to wear a mask. Firstly, the algorithm introduces the residual structure of structural reparameterization in the feature extraction network named Darknet53 of YOLOv3 to obtain the input features;Secondly, the SimSPPF (Simplified Spatial Pyramid Pooling-Fast) is introduced to enhance feature extraction;Finally, an improved attention mechanism is introduced to make the model focus on regions with more prominent features. Besides, in order to ensure the accuracy of target detection, CIoU and Focal loss function was used in the training process. The results show that compared with the traditional YOLOv3, the detection accuracy of the improved algorithm for normal face and mask face is improved by 16.98% and 7.30% respectively, and the mAP is improved by 12.14%, which can meet the requirements of daily use and lay a foundation for rapid face recognition when wearing mask. () © 2023 IEEE.

Evaluation of infection probability in a multiroom office space using computational fluid dynamics coupled with Wells-Riley model

The current COVID-19 pandemic has highlighted the importance of health safety assessment in various indoor scenarios. Computational fluid dynamics (CFD) combined with a modified Wells-Riley equation provides a powerful tool to analyse local infection probability in an indoor space. Compared to a single infection probability characterising the space in the traditional Wells-Riley model, the coupled approach provides a distribution of infection probability within the space. Furthermore, this approach avoids assuming a well-mixed state, usually related to Wells-Riley equation. This study compares displacement and mixing ventilation strategies with four different ventilation rates to assess the local quanta concentrations modelled using passive scalar transport approach. The simulation results are processed to also account for the effect of wearing masks and vaccinations. The result show that a well-designed displacement ventilation system can significantly reduce infection probability compared to mixing ventilation system at similar airflow rate. Additionally, the results emphasised the importance of wearing mask and getting vaccinated as a means of reducing infection probability. © 2022 17th International Conference on Indoor Air Quality and Climate, INDOOR AIR 2022. All rights reserved.

Mask Wear Detection Algorithm Based on YOLOv5m

Wearing a mask during the COVID-19 epidemic can effectively prevent the spread of the virus. In view of the problems of small target size, crowd blocking each other and dense arrangement of targets in crowded places, a target detection algorithm based on the improved YOLOv5m model is proposed to achieve efficient detection of whether a mask is worn or not. This paper introduces four attention mechanisms in the feature extraction network based on the YOLOv5m model to suppress irrelevant information, enhance the information representation of the feature map, and improve the detection capability of the model for small-scale targets. The experimental results showed that the introduction of the SE module increased the mAP value of the original network by 9.3 percentage points, the most significant increase among the four attention mechanisms. And then a dual-scale feature fusion network is used in the Neck layer, giving different weights to the feature layers to convey more effective feature information. In the image pre-processing, the Mosaic method was used for data enhancement, and the CIoU loss function was used for coordinate frame positioning in the prediction layer. Experiments on the improved YOLOv5m algorithm demonstrate that the mean recognition accuracy of the method improves by 10.7 percentage points over the original method while maintaining the original model size and detection speed, and better solves the problems of small scale, dense arrangement and mutual occlusion of targets in mask wearing detection tasks in crowded places. © 2023 IEEE.

Boosting Masked Face Recognition with Multi-Task ArcFace

In this article, we tackle the recognition of faces wearing surgical masks. Surgical masks have become a necessary piece of daily apparel because of the COVID-19-related worldwide health problem. Modern face recognition models are in trouble because they were not made to function with masked faces. Furthermore, in order to stop the infection from spreading, apps capable of detecting if the individuals are wearing masks are also required. To address these issues, we present an end-to-end approach for training face recognition models based on the ArcFace architecture, including various changes to the backbone and loss computation. We also use data augmentation to generate a masked version of the original dataset and mix them on the fly while training. Without incurring any additional computational costs, we modify the chosen network to output also the likelihood of wearing a mask. Thus, the face recognition loss and the mask-usage loss are merged to create a new function known as Multi-Task ArcFace (MTArcFace). The conducted experiments demonstrate that our method outperforms the baseline model results when faces with masks are considered, while achieving similar metrics on the original dataset. In addition, it obtains a 99.78% of mean accuracy in mask-usage classification. © 2022 IEEE.

Real Time AI Based Face Mask Detector

The present Covid-19 pandemic, face mask detection identifying significant forward movement in the fields of image and computer observation. Several face detection models were developed utilizing various methods and techniques. The dataset arrangement supplied in this work, which was gathered from multiple sources, could be utilized by other to develop more complex representation such as those for facial identification software, facial positions, and facial component identification. The goal of project 'Real Time AI Based Face Mask Detector', It is develop a tool that really can identify a person image and to affect whether he or she is wearing a mask. COVID makes it necessary to wear a face mask to keep it safe. As the country begins to reopen in stages, face masks have become a crucial part of our everyday life to keep safe. Face masks will be essential for socializing and conducting business. As a result, this software uses a camera to notice whether a person is wearing a mask or not. © 2022 IEEE.

Non-Contact Physiological Measurement System for Wearing Masks During the Epidemic

Physiological signals indicate a person's physical and mental state at any given time. Accordingly, many studies extract physiological signals from the human body with non-contact methods, and most of them require facial feature points. However, under COVID-19, wearing a mask has become a must in many places, so how non-contact physiological information measurements can still be performed correctly even when a mask covers the facial information has become a focus of research. In this study, RGB and thermal infrared cameras were used to execute non-contact physiological information measurement systems for heart rate, blood pressure, respiratory rate, and forehead temperature for people wearing masks due to the pandemic. Using the green (G) minus red (R) signal in the RGB image, the region of interest (ROI) is established in the forehead and nose bridge regions. The photoplethysmography (PPG) waveforms of the two regions are obtained after the acquired PPG signal is subjected to the optical flow method, baseline drift calibration, normalization, and bandpass filtering. The relevant parameters in Deep Neural Networks (DNN) for the regression model can correctly predict the heartbeat and blood pressure. In addition, the temperature change in the ROI of the mask after thermal image processing and filtering can be used to correctly determine the number of breaths. Meanwhile, the thermal image can be used to read the temperature average of the ROI of the forehead, and the forehead temperature can be obtained smoothly. The experimental results show that the above-mentioned physiological signals of a subject can be obtained in 6-s images with the error for both heart rate and blood pressure within 2%∼3% and the error of forehead temperature within ±0.5°C. © 2023 Tech Science Press. All rights reserved.

SCN-SAM: A Modified Self-Cure Network for Facial Expression Recognition under Face Masks

Due to COVID-19, wearing masks has become more common. However, it is challenging to recognize expressions in the images of people wearing masks. In general facial recognition problems, blurred images and incorrect annotations of images in large-scale image datasets can make the model's training difficult, which can lead to degraded recognition performance. To address this problem, the Self-Cure Network (SCN) effectively suppresses the over-fitting of the network to images with uncertain labeling in large-scale facial expression datasets. However, it is not clear how well the SCN suppresses the uncertainty of facial expression images with masks. This paper verifies the recognition ability of SCN on images of people wearing masks and proposes a self-adjustment module to further improve SCN (called SCN-SAM). First, we experimentally demonstrate the effectiveness of SCN on the masked facial expression dataset. We then add a self-adjustment module without extensive modifications to SCN and demonstrate that SCN-SAM outperforms state-of-the-art methods in synthetic noise-added FER datasets. © 2023 Global IT Research Institute (GiRI).

An Effective Technique using MobileNet-V2 for Face Mask Detection

Recently, the widespread and extremely fatal disease known as the coronavirus spread throughout the entire world. China's Wuhan city served as its first hub for its spread. The COVID-19 outbreak has briefly disrupted our daily routines by affecting worldwide trade and travel. Precautions include hand washing, using hand sanitizer, keeping a safe distance, and most importantly wearing a mask. However, putting on a mask that prevents to some extent airborne droplet transmission will be helpful as a precautionary measure in this pandemic. In the near future, many public service providers will ask the customers to wear masks correctly to avail of their services. However, ensuring that everyone wears a face mask is a difficult chore. Many techniques such as Machine Learning, Deep learning models like CNN, RNN, MobileNet etc. are available to solve this problem. This paper presents a simplified approach using MobileNet-V2 for Face Mask Detection. The model is developed by utilizing TensorFlow, Keras, OpenCV, and Scikit-Learn. The face mask detection model's objective is to identify people's faces and determine whether they are wearing masks at the time they are recorded in the image. An alert will sound if there is a desecration on the scene or in public areas. The challenge with the model is to detect the face mask during motion of a person. Precision, recall, F1-score, support, and accuracy are used to evaluate the system's performance and show its practical pertinency. The system operates with a 99.9% F1 score. The currently developed model will be used in conjunction with embedded camera infrastructure which may then be used to a variety of verticals, including schools, universities, public spaces, airport terminals/gates, etc. © 2023 IEEE.