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.

Generating Masked Facial Datasets Using Dlib-Machine Learning Library

In 2020, the COVID-19 pandemic spread globally, leading to countries imposing health restrictions on people, including wearing masks, to prevent the spread of the disease. Wearing a mask significantly decreases distinguishing ability due to its concealment of the main facial features. After the outbreak of the pandemic, the existing datasets became unsuitable because they did not contain images of people wearing masks. To address the shortage of large-scale masked faces datasets, a developed method was proposed to generate artificial masks and place them on the faces in the unmasked faces dataset to generate the masked faces dataset. Following the proposed method, masked faces are generated in two steps. First, the face is detected in the unmasked image, and then the detected face image is aligned. The second step is to overlay the mask on the cropped face images using the dlib-ml library. Depending on the proposed method, two datasets of masked faces called masked-dataset-1 and masked-dataset-2 were created. Promising results were obtained when they were evaluated using the Labeled Faces in the Wild (LFW) dataset, and two of the state-of-the-art facial recognition systems for evaluation are FaceNet and ArcFace, where the accuracy of using the two systems was 96.1 and 97, respectively with masked-dataset-1 and 87.6 and 88.9, respectively with masked-dataset-2. © 2022 IEEE.

Face Mask Detection Using Convolution Neural Network

Face recognition in the industry now is playing an important role in each sector. Each person has different type of features and face;therefore, each identity is unidentical. In this COVID outbreak, a major crisis has occurred due to which preventions are to be made. One such prevention is use of a face mask which is very much important. Nowadays, various firms and organizations are using facial recognition systems for their own general purpose. We all know that it has now been a crucial task to wear a mask every time, when we go somewhere. But as we know it is not possible to keep track of who wears a mask and who does not. We make the use of AI in our daily life. We achieve this with the help of a neural network system, which we train so that it can further describe people's features. Even though the original dataset was limited, the Convolutional Neural Network (CNN) model achieved exceptional accuracy utilizing the deep learning technique. With the use of a face mask detection dataset that contains both with and without face mask photographs, we are able to recognize faces in real-time from a live webcam stream using OpenCV. We will develop a COVID-19 face mask detection system using our dataset, along with Python, OpenCV, Tensor Flow, and Keras. © 2022 IEEE.

Improving Masked Face Recognition Using Dense Residual Unit Aided with Quadruplet Loss

All over the world, people are wearing face masks and practising social distancing to protect themselves against the Coronavirus disease (COVID-19). The need for contactless biometric systems has increased to avoid the common point of contact. Among contactless biometric systems, facial recognition systems are the most economical and effective ones. Conventional face recognition systems rely heavily upon the facial features of the eyes, nose, and mouth. But due to people wearing face masks, the important facial features of the nose and mouth get hidden under the mask, resulting in degraded performance by the facial recognition systems on masked faces. In this paper, we propose a Dense Residual Unit (DRU) aided with Quadruplet loss on top of existing facial recognition systems. This solution tries to unveil the masked faces by producing embeddings for masked faces, which are similar to embeddings of unmasked faces of the same identity but different from embeddings of different identities. We have evaluated our method using two pre-trained facial recognition models' backbones, i.e. Resnet-101 and MobileFaceNet, and upon two datasets, among them, one is a real-world dataset, i.e. MFR2, and one is a simulated masked face dataset i.e. masked version of LFW. We have achieved improvement in the performance of masked face recognition in terms of False Match Rate, False Non-Match Rate, Fisher Discriminant ratio, and Equal Error Rate. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Processing of Images Based on Machine Learning to Avoid Unauthorized Entry

The proposal of a facial recognition system to increase security, through facial recognition with multiple utilities such as facilitating the access of people with adequate protection measures in times of Covid-19, as well as security when seeking to hide their identity. The methodology considers the use of tools such as Python and OpenCV, as well as models such as Eigen Faces, Fisher Faces, and LBPH Faces, as units of analysis are considered photographs and portions of the video that capture facial expressions that then their patterns are trained with facial recognition algorithms. The results obtained show that the LBPH Faces obtained confidence values lower than 70, with a 95% certainty of recognition and a shorter recognition time, improving the accuracy of facial recognition, also with the increase of the data was achieved to improve the accuracy of recognition as well as improve confidence regarding the safety of people. © 2022 IEEE.

Multi-Model Face Liveness Detection Via Gaze Detection and Convolutional Neural Networks

Spoofing attacks pose a significant threat to facial recognition systems. There are many types of attacks that can be carried out, ranging from photo attacks to mask attacks. Facial recognition systems must defend themselves against such attacks with cutting-edge anti-spoofing countermeasures. The current Covid-19 outbreak has increased the need for facial recognition, exacerbating the issue of secure facial recognition systems. Many existing liveness detection methods fail to defend against all types of attacks because they exclude mask attacks. This is a flaw in many methods, and because this is the only method of defense, there is no redundancy. In this paper, we propose a multi-model liveness detection model that employs gaze detection and Convolutional Neural Networks (CNN) to provide increased defense against multiple types of spoofing attacks while also increasing robustness. We were able to achieve 100 percent accuracy against photo and video attacks using gaze detection, and 95.28 percent accuracy against photos, videos, and mask attacks using a CNN. The multi-model system achieved an aggregate accuracy of 99.85 percent. © 2022 IEEE.

Face Authentication from Masked Face Images Using Deep Learning on Periocular Biometrics

Nowadays, identity theft is an alarming issue with the growth of e-commerce and online services. Moreover, due to the Covid-19 pandemic, society has been pushed towards the usage of masks for people to safely interact with one another. It is hard to recognize a person if the face is mostly covered, even more so to artificial intelligence who have more difficulty identifying a masked individual. To further protect personal information and to develop a secure information system, more comprehensive bio-metric approaches are required. The currently used facial recognition systems are using biometrics such as periocular regions, iris, face, skin tone and racial information etc. In this paper, we apply a deep learning-based authentication approach using periocular biometric information to enhance the performance of the facial recognition system. We used the Real-World Masked Face Dataset (RMFD) and other datasets to develop our system. We implemented some experiments using CNN model on the periocular region information of the images. Hence, we developed a system that can recognize a person from only using a small region of face, which in this case is the periocular information including both eyes and eyebrows region. There is only a focus on the periocular region with our model in the view of the fact that the periocular region of the face is the main reliable source of information we can get while a person is wearing a face mask. © 2022, Springer Nature Switzerland AG.

Ingenious Methodology to Detect Disguised Human Faces with Masks using Deep Neural Network

Face recognition is now ubiquitous as an efficient and non-invasive method to verify identity. A facial recognition system works by comparison of a digital image or video frame showing a person's face with a database storing face images. Face masks are considered a required biosafety measure during this COVID-19 pandemic. Use of masks led to various issues to emerge and impact the functioning of earlier facial recognition algorithms and that has motivated our research. The construction of a real-time face recognition system that recognizes faces with and without masks is described in this paper. ResNet10 is used to perform the feature extraction. Then, to perform face detection and recognition, it is paired with a machine learning algorithm such as SVM. Without a mask, the maximum recognition accuracy is 99.40%, while with a mask, it is 98.30%. © 2022 IEEE.

Face Recognition based Artificial Intelligence With AttendX Technology for Student Attendance

AttendX is a platform that uses a facial recognition system to perform attendance. AttendX is a solution for attendance systems that exist in the scope of work or agency. AttendX can make attendance activities more efficient because of its features, making it easier for users to attend. To register AttendX, only use the face (left, right, front side, wearing a mask) and a brief bio of the person who registers. AttendX can verify the face of the user who has registered and is stored in the database. This application is designed with high-speed facial recognition technology. It can be used to solve the current problem, preventing the spread of the covid-19 virus, because AttendX can also recognize the user's face when wearing a mask. This study provides a real-world view of technological developments, significantly facilitating the use of facial recognition technology to complement those presented on the Internet, the latest face recognition and verification, and propose possible use cases for various applications. AttendXN et facial recognition function, the method used is ResNet and a hierarchical feedforward network to achieve the planned results. © 2022 IEEE.

Leveraging Discriminative Cues for Masked Face Recognition in Post COVID World

The post COVID world has completely disrupted our lifestyle, where wearing a mask is necessary to protect ourselves and others from contracting the virus. However, face masks have proved to be challenging for facial biometric systems, in the sense that these systems do not work as expected when wearing masks as nearly half of the face is covered, thus reducing discriminative features that the model can leverage. Most of the existing frameworks rely on the entire face as the input, but as the face is covered, these frameworks do not perform up to the mark. Moreover, training another facial recognition system with mask images is challenging as the availability of datasets is limited, both qualitatively and quantitatively. In this paper, we propose a framework that shows better results without significant training. In the proposed work, firstly we extracted the face using SSD, then by obtaining Facial Landmarks for utilizing the cues from other dis-criminative parts for facial recognition. The proposed framework is able to out-perform other frameworks on facial mask images and also found ~4.5% increment in accuracy. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Implementation of an Embedded Masked Face Recognition System using Huskylens System-On-Chip Module

Globally, Facial recognition systems have been increasingly adopted, by governments, as a viable means of identification and verification in public spaces such as the airport, train stations, and stadiums. However, in the wake of the COVID-19 outbreak, the World Health Organization (WHO) declared that wearing face masks is an essential safety precaution. As a result, current facial recognition systems have difficulties recognizing faces accurately, which motivated this study. This research aims to implement an embedded masked face recognition system using the HuskyLens SoC module to identify people, even while wearing a face mask. The developed method was actualized using the Kendryte K210 chip embedded in the HuskyLens module. This system-on-chip design was integrated with other peripherals using an Arduino Pro-mini board. The results of testing and evaluating the system's performance show that the system's facial recognition accuracy with masked and without masks faces was 90% and 95%, respectively. Implementing this solution in our environment would enable accurate real-time recognition of masked and unmasked faces © 2022 IEEE.

Face Mask Wear Detection by using Facial Recognition System for Entrance Authorization

A Face Mask Wear Detection Device for Entrance Authorization is designed to ensure that everyone wears a face mask at all times in a confined space. It is one of the easiest methods to lower the rate of coronavirus infection and hence save lives. Asthma, high blood pressure, heart failure, and many other chronic conditions can be fatal to those who are infected by the novel Coronavirus (nCoV-21). Consequently, the goal of this research is for face mask wear detection devices that help to reduce the rate of Novel Coronavirus infection on-premises or in public places by ensuring that customers comply with Standard Handling Procedures (SOP) set by the Ministry of Malaysian Health (MOH). Customers' faces are recognized by this device whether or not they are covered by a face mask upon entry into a facility. Additionally, the use of this device can contribute to ensuring compliance with the maximum number of customers allowed on the premises. A facial recognition system is the goal of this study that uses technology designed as an individual disciplinary aid and follows the safety procedure at this critical time. This research was developed using the engineering design process development model which has four phases namely;identifying the problem, making possible solutions, prototype development and testing and evaluating the solution. Results indicate that the developed product can function effectively. Experts have discovered that using this product helps people stick to their face mask routines. The design of this product has improved, which means that the overall quality of the product is elevated to be capable of performing as intended in terms of intelligent technologies © 2022. International Journal of Advanced Computer Science and Applications.All Rights Reserved.

Identification of Non-Vaccinated People Using Face Recognition Based on CNN

Preventive medical care relies on vaccinations to provide significant health benefits. Vaccination is an important and effective preventive health measure. There is no better way to reduce the risk of pandemic spread of SARS-CoV-2/COVID-19 than vaccination. As a preventive measure, the government has begun vaccinating Indians against Corona infection. It is therefore important, in addition to developing and supplying vaccines, that enough people are willing to obtain vaccines. However, of the populations worldwide, there are concerning proportions that are reluctant to get vaccinated. In order to end the pandemic, it is highly essential to deal with another omnipresent issue: outright rejection of vaccinations. To achieve population immunity first we have to find the non-vaccinated population should be detected and to this end, this project proposed an Aadhaar-based facial recognition system is used to find non-vaccinated citizen and alert them using Artificial Intelligence. Deep learning which is in the form of Convolutional Neural Networks (CNNs) are used to carry out the face recognition process and it is also proven to be an efficient method to carry out face recognition due to its high fidelity. A CNN is a Deep Neural Network (DNN), which is designed to perform challenging tasks like image processing, which is crucial for facial recognition. The CNN structure is composed of numerous layers of neurons that connect the neurons: an input layer, an output layer, and layers between these two layers. In the midst of the epidemic coronavirus outbreak (COVID-19), a person's current inoculation status will be updated based on face recognition to safeguard him/her from COVID-19 and it may also serve as proof of vaccination for other purposes. Facial recognition technology (FRT) along with the Aadhaar helps to authenticate people before entering into any types of service. This project provides COVID-19 immunization status, which is determined by observing at their face, and certify that they have been vaccinated. © 2022 IEEE.

FaceNet with RetinaFace to Identify Masked Face

The use of masks due to the Covid-19 pandemic reduces the accuracy of facial recognition systems applied to camera-based security systems. The use of the mask by the people covers most of the facial featureswhich is located from middle to bottom area. In addition, the area which are still visible are the upper face which are eyes and forehead. This paper proposes a masked face recognition using a combination of RetinaFace as a face detector and FaceNet as a face recognizer. The MFR2 dataset with 53 identities was used to train and test this method. The test data in this study are only images of masked faces. Cosine Distance was implemented to measure the face similarity. Based on the experiment results, the proposed method obtained 98.2% of detection accuracy. The proposed method provided 78% accurate performance with 3.63 s for processing a single frame in terms of face recognition. The performance indicates that our system can potentially be applied in security systems with many different identities. © 2021 IEEE.

Survey of Face Liveness Detection for Unsupervised Locations

Spoofing attacks represent a major threat to facial recognition systems. There are many types of attacks that can be carried out, ranging from 2D photo attacks to 3D mask attacks. Facial recognition systems must defend against such attacks using state-of-the-art anti-spoofing countermeasures. The current Covid-19 outbreak has increased the need for facial recognition, exacerbating the issue of secure facial recognition systems. This paper contains an overview of face liveness detection methods, mainly in the domain of deep learning, and how these methods combat the threat of non-live faces. © 2021 IEEE.