Face Mask Assistant: Detection of Face Mask Service Stage Based on Mobile Phone

The continuous COVID-19 upsurge and emerging variants present unprecedented challenges in many health systems. Many regulatory authorities have instituted the mandatory use of face masks especially in public places where massive contact of people is frequent and inevitable, particularly inside public transport facilities, sports arenas, shopping malls and workplaces. However, compliance and adherence to proper wearing of face masks have been difficult due to various reasons including diversified mask types, different degrees of obstructions, various variations, balancing various model detection accuracy or errors and deployment requirements, angle of view, deployment of detection model on computers with limited processing power, low-resolution images, facial expression, and lack of real-world dataset. Therefore, this study aimed at providing a comprehensive review of artificial intelligence models that have been used to detect face masks. The study revealed that deep learning models such as the Inceptionv3 convolutional neural network achieved 99.9% accuracy in detecting COVID-19 face masks. We deducted that most of the datasets used to detect face masks are created artificially, do not represent the real-world environments which ultimately affect the precision accuracy of the model when deployed in the real world. Hence there is a need for sharing real-world COVID-19 face mask images for modelling deep learning techniques. The study also revealed that deeper and wider deep learning architectures with increased training parameters, such as inception-v4, Mask R-CNN, Faster R-CNN, YOLOv3, Xception, and DenseNet are not yet implemented to detect face masks.

show abstract

“… The image dataset used was not specified. Face Mask Assistant [45] . A detection system based on the mobile phone.…”

Section: Resultsmentioning

confidence: 99%

Application of deep learning and machine learning models to detect COVID-19 face masks - A review

Mbunge

Simelane

Fashoto

et al. 2021

Sustainable Operations and Computers

View full text Add to dashboard Cite

show abstract

…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…Accuracy was defined as the ratio with the sum of TP and TN and the sum of TP, FP, FN, and TN. The F1 score was defined as the harmonic mean of RE and PR [38], where RE and PR is the recall and precision, respectively. The quantification results acquired by BMO and the anterior LC curve with its parameters can indicate the shape of the post-processing and the anterior LC surface.…”

Section: Fine Segmentation Performance Analysismentioning

confidence: 99%

Automatic Quantification of Anterior Lamina Cribrosa Structures in Optical Coherence Tomography Using a Two-Stage CNN Framework

Rahman

Jeong

Kim

et al. 2021

Sensors

View full text Add to dashboard Cite

In this study, we propose a new intelligent system to automatically quantify the morphological parameters of the lamina cribrosa (LC) of the optical coherence tomography (OCT), including depth, curve depth, and curve index from OCT images. The proposed system consisted of a two-stage deep learning (DL) model, which was composed of the detection and the segmentation models as well as a quantification process with a post-processing scheme. The models were used to solve the class imbalance problem and obtain Bruch’s membrane opening (BMO) as well as anterior LC information. The detection model was implemented by using YOLOv3 to acquire the BMO and LC position information. The Attention U-Net segmentation model is used to compute accurate locations of the BMO and LC curve information. In addition, post-processing is applied using polynomial regression to attain the anterior LC curve boundary information. Finally, the numerical values of morphological parameters are quantified from BMO and LC curve information using an image processing algorithm. The average precision values in the detection performances of BMO and LC information were 99.92% and 99.18%, respectively, which is very accurate. A highly correlated performance of R2 = 0.96 between the predicted and ground-truth values was obtained, which was very close to 1 and satisfied the quantification results. The proposed system was performed accurately by fully automatic quantification of BMO and LC morphological parameters using a DL model.

show abstract

“…Chen et al, in [17], have developed a mobile application that allows us to determine the service life of a facemask, indicating what period it is in, in addition to telling us what its level of effectiveness is after a period of use. To do this, they use microphotographs by extracting four characteristics of gray, employing co-occurrence matrices (GLCM) from the microphotographs of the facial mask.…”

Section: Related Workmentioning

confidence: 99%

Incorrect Facemask-Wearing Detection Using Convolutional Neural Networks with Transfer Learning

et al. 2021

View full text Add to dashboard Cite

The COVID-19 pandemic has been a worldwide catastrophe. Its impact, not only economically, but also socially and in terms of human lives, was unexpected. Each of the many mechanisms to fight the contagiousness of the illness has been proven to be extremely important. One of the most important mechanisms is the use of facemasks. However, the wearing the facemasks incorrectly makes this prevention method useless. Artificial Intelligence (AI) and especially facial recognition techniques can be used to detect misuses and reduce virus transmission, especially indoors. In this paper, we present an intelligent method to automatically detect when facemasks are being worn incorrectly in real-time scenarios. Our proposal uses Convolutional Neural Networks (CNN) with transfer learning to detect not only if a mask is used or not, but also other errors that are usually not taken into account but that may contribute to the virus spreading. The main problem that we have detected is that there is currently no training set for this task. It is for this reason that we have requested the participation of citizens by taking different selfies through an app and placing the mask in different positions. Thus, we have been able to solve this problem. The results show that the accuracy achieved with transfer learning slightly improves the accuracy achieved with convolutional neural networks. Finally, we have also developed an Android-app demo that validates the proposal in real scenarios.

show abstract

Face Mask Assistant: Detection of Face Mask Service Stage Based on Mobile Phone

Cited by 49 publications

References 53 publications

Application of deep learning and machine learning models to detect COVID-19 face masks - A review

Application of deep learning and machine learning models to detect COVID-19 face masks - A review

Automatic Quantification of Anterior Lamina Cribrosa Structures in Optical Coherence Tomography Using a Two-Stage CNN Framework

Incorrect Facemask-Wearing Detection Using Convolutional Neural Networks with Transfer Learning

Contact Info

Product

Resources

About