scholarly journals Face Mask Detection in Real-Time using MobileNetv2

2021 ◽  
Vol 10 (6) ◽  
pp. 104-108
Author(s):  
Mohamed Almghraby ◽  
◽  
Abdelrady Okasha Elnady* ◽  
Keyword(s):  
Real Time ◽  
Face Mask ◽  
Stochastic Gradient Descent ◽  
Training Dataset ◽  
Optimization Approach ◽  
Public Places ◽  
Application Systems ◽  
Develop Software ◽  
Video Feed ◽  
Maximal Peak

Face mask detection has made considerable progress in the field of computer vision since the start of the Covid-19 epidemic. Many efforts are being made to develop software that can detect whether or not someone is wearing a mask. Many methods and strategies have been used to construct face detection models. A created model for detecting face masks is described in this paper, which uses “deep learning”, “TensorFlow”, “Keras”, and “OpenCV”. The MobilenetV2 architecture is used as a foundation for the classifier to perform real-time mask identification. The present model dedicates 80 percent of the training dataset to training and 20% to testing, and splits the training dataset into 80% training and 20% validation, resulting in a final model with 65 percent of the dataset for training, 15 percent for validation, and 20% for testing. The optimization approach used in this experiment is “stochastic gradient descent” with momentum (“SGD”), with a learning rate of 0.001 and momentum of 0.85. The training and validation accuracy rose until they reached their maximal peak at epoch 12, with 99% training accuracy and 98% validation accuracy. The model's training and validation losses both reduced until they reached their lowest at epoch 12, with a validation loss of 0.050% and a training loss of less than 0.025%. This system allows for real-time detection of someone is missing the appropriate face mask. This model is particularly resource-efficient when it comes to deployment, thus it can be employed for safety. So, this technique can be merged with embedded application systems at public places and public services places as airports, trains stations, workplaces, and schools to ensure subordination to the guidelines for public safety. The current version is compatible with both IP and non-IP cameras. Web and desktop apps can use the live video feed for detection. The program can also be linked to the entrance gates, allowing only those who are wearing masks to enter. It can also be used in shopping malls and universities.

scholarly journals Face Mask Detection System using Mobilenetv2

2021 ◽  
Vol 10 (4) ◽  
pp. 127-129
Author(s):  
Mayank Arora ◽  
Sarthak Garg ◽  
Srivani A.
Keyword(s):  
Feature Detection ◽  
Detection System ◽  
Face Mask ◽  
Image Feature ◽  
Raspberry Pi ◽  
Computationally Efficient ◽  
Public Places ◽  
Application Systems ◽  
Develop Software ◽  
The Face

In this pandemic, it is getting more and more difficult to keep a track of people who are wearing masks regularly or not. It cannot solely depend on human efforts to take care of this task and therefore there is a need to develop software that can automatically detect whether any given person is wearing a mask or not. Face Detection has evolved as a really popular problem in image processing and computer vision. Many new algorithms are being devised using convolutional architectures to form the algorithm as accurately as possible. These convolutional architectures have made it possible to extract even the pixel details. Training is performed through Fully Convolutional Neural Networks to semantically segment out the faces present in that image. Feature detection and feature extraction techniques help us identify whether a person is wearing a mask or not. The face mask detector will use a dataset of morphed masked images. Therefore, the created model will be accurate and it will also be computationally efficient and easily deployable in embedded systems since the MobileNetV2 architecture will be incorporated (Raspberry Pi, Google Coral, etc.). This framework can also be used in real-time applications that, due to the outbreak of Covid-19, require face-mask detection for safety purposes. This project can be merged with embedded application systems at airports, train stations, workplaces, schools, and public places to ensure compliance with the guidelines for public safety. The above topic is very prominent in recent times as the identification process will not only help us classify individuals but also will reduce the workforce required to do the same exponentially.

scholarly journals Face Mask Detection System

2021 ◽  
Vol 9 (VII) ◽  
pp. 1400-1402
Author(s):  
Yatharth Khansali
Keyword(s):  
Real Time ◽  
Detection System ◽  
Face Mask ◽  
World Health ◽  
Public Places ◽  
The World ◽  
The Face ◽  
Time Requirements ◽  
Health Organization ◽  
Protective Mask

COVID-19 pandemic has affected the world severely, according to the World Health Organization (WHO), coronavirus disease (COVID-19) has globally infected over 176 million people causing over 3.8 million deaths. Wearing a protective mask has become a norm. However, it is seen in most public places that people do not wear masks or don’t wear them properly. In this paper, we propose a high accuracy and efficient face mask detector based on MobileNet architecture. The proposed method detects the face in real-time with OpenCV and then identifies if it has a mask on it or not. As a surveillance task, it supports motion, and is trained using transfer learning and compared in terms of both precision and efficiency, with special attention to the real-time requirements of this context.

scholarly journals Real Time Face Mask Identification Using Deep Learning

2021 ◽  
Vol 1916 (1) ◽  
pp. 012077
Author(s):  
M Sujaritha ◽  
S Kabilan ◽  
M Manikandan ◽  
S Nanda Kisore
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Face Mask

A Novel Corrosion Monitoring and Prediction System Utilizing Advanced Artificial Intelligence

2021 ◽  
Author(s):  
Klemens Katterbauer ◽  
Waleed Dokhon ◽  
Fahmi Aulia ◽  
Mohanad Fahmi
Keyword(s):  
Real Time ◽  
Oil And Gas ◽  
Salt Water ◽  
Oil And Gas Industry ◽  
Training Dataset ◽  
Metal Loss ◽  
Corrosion Monitoring ◽  
Prediction System ◽  
Well Performance ◽  
Data Driven Approach

Abstract Corrosion in pipes is a major challenge for the oil and gas industry as the metal loss of the pipe, as well as solid buildup in the pipe, may lead to an impediment of flow assurance or may lead to hindering well performance. Therefore, managing well integrity by stringent monitoring and predicting corrosion of the well is quintessential for maximizing the productive life of the wells and minimizing the risk of well control issues, which subsequently minimizing cost related to corrosion log allocation and workovers. We present a novel supervised learning method for a corrosion monitoring and prediction system in real time. The system analyzes in real time various parameters of major causes of corrosion such as salt water, hydrogen sulfide, CO2, well age, fluid rate, metal losses, and other parameters. The data are preprocessed with a filter to remove outliers and inconsistencies in the data. The filter cross-correlates the various parameters to determine the input weights for the deep learning classification techniques. The wells are classified in terms of their need for a workover, then by the framework based on the data, utilizing a two-dimensional segmentation approach for the severity as well as risk for each well. The framework was trialed on a probabilistically determined large dataset of a group of wells with an assumed metal loss. The framework was first trained on the training dataset, and then subsequently evaluated on a different test well set. The training results were robust with a strong ability to estimate metal losses and corrosion classification. Segmentation on the test wells outlined strong segmentation capabilities, while facing challenges in the segmentation when the quantified risk for a well is medium. The novel framework presents a data-driven approach to the fast and efficient characterization of wells as potential candidates for corrosion logs and workover. The framework can be easily expanded with new well data for improving classification.

scholarly journals Learning-Type Anchors-Driven Pose Estimation for the Autolanding Fixed-Wing UAVs

2021 ◽  
Author(s):  
Dengqing Tang ◽  
Lincheng Shen ◽  
Xiaojiao Xiang ◽  
Han Zhou ◽  
Tianjiang Hu
Keyword(s):  
Real Time ◽  
Pose Estimation ◽  
Stereo Vision ◽  
Vision System ◽  
Estimation Method ◽  
Satellite System ◽  
Training Dataset ◽  
Estimation Accuracy ◽  
The Impact ◽  
Outdoor Experiments

<p>We propose a learning-type anchors-driven real-time pose estimation method for the autolanding fixed-wing unmanned aerial vehicle (UAV). The proposed method enables online tracking of both position and attitude by the ground stereo vision system in the Global Navigation Satellite System denied environments. A pipeline of convolutional neural network (CNN)-based UAV anchors detection and anchors-driven UAV pose estimation are employed. To realize robust and accurate anchors detection, we design and implement a Block-CNN architecture to reduce the impact of the outliers. With the basis of the anchors, monocular and stereo vision-based filters are established to update the UAV position and attitude. To expand the training dataset without extra outdoor experiments, we develop a parallel system containing the outdoor and simulated systems with the same configuration. Simulated and outdoor experiments are performed to demonstrate the remarkable pose estimation accuracy improvement compared with the conventional Perspective-N-Points solution. In addition, the experiments also validate the feasibility of the proposed architecture and algorithm in terms of the accuracy and real-time capability requirements for fixed-wing autolanding UAVs.</p>

scholarly journals Development of detection method for automatic hemostasis using machine learning with abdominal cavity irrigation

2020 ◽  
Vol 7 (7) ◽  
pp. 2103
Author(s):  
Yoshihisa Matsunaga ◽  
Ryoichi Nakamura
Keyword(s):  
Machine Learning ◽  
Minimally Invasive Surgery ◽  
Minimally Invasive ◽  
Real Time ◽  
Invasive Surgery ◽  
Abdominal Cavity ◽  
Training Dataset ◽  
Support Vector ◽  
Processing Cost ◽  
Surgical Field

Background: Abdominal cavity irrigation is a more minimally invasive surgery than that using a gas. Minimally invasive surgery improves the quality of life of patients; however, it demands higher skills from the doctors. Therefore, the study aimed to reduce the burden by assisting and automating the hemostatic procedure a highly frequent procedure by taking advantage of the clearness of the endoscopic images and continuous bleeding point observations in the liquid. We aimed to construct a method for detecting organs, bleeding sites, and hemostasis regions.Methods: We developed a method to perform real-time detection based on machine learning using laparoscopic videos. Our training dataset was prepared from three experiments in pigs. Linear support vector machine was applied using new color feature descriptors. In the verification of the accuracy of the classifier, we performed five-part cross-validation. Classification processing time was measured to verify the real-time property. Furthermore, we visualized the time series class change of the surgical field during the hemostatic procedure.Results: The accuracy of our classifier was 98.3% and the processing cost to perform real-time was enough. Furthermore, it was conceivable to quantitatively indicate the completion of the hemostatic procedure based on the changes in the bleeding region by ablation and the hemostasis regions by tissue coagulation.Conclusions: The organs, bleeding sites, and hemostasis regions classification was useful for assisting and automating the hemostatic procedure in the liquid. Our method can be adapted to more hemostatic procedures. 

Sign in / Sign up

Export Citation Format

Share Document