MASKED FACE RECOGNITION VIA SELF-ATTENTION BASED LOCAL CONSISTENCY REGULARIZATION

With the COVID-19 pandemic, one critical measure against infection is wearing masks. This measure poses a huge challenge to the existing face recognition systems by introducing heavy occlusions. In this paper, we propose an effective masked face recognition system. To alleviate the challenge of mask occlusion, we first exploit RetinaFace to achieve robust masked face detection and alignment. Secondly, we propose a deep CNN network for masked face recognition trained by minimizing ArcFace loss together with a local consistency regularization (LCR) loss. This facilitates the network to simultaneously learn globally discriminative face representations of different identities together with locally consistent representations between the non-occluded faces and their counterparts wearing synthesized facial masks. The experiments on the masked LFW dataset demonstrate that the proposed system can produce superior masked face recognition performance over multiple state-of-the-art methods. The proposed method is implemented in a portable Jetson Nano device which can achieve real-time masked face recognition. © 2022 IEEE.

Masked Face Detection using Lightweight Deep Learning based Model for IoT based Healthcare applications

One of the best measures to enforce in epidemiological scenarios, such as the present COVID-19 epidemic, is the usage of masks. For a while, this will be a regular part of life, notably in public places. In order to deal with these unusual circumstances where people who wear mask are being watched, there is a need for an effective face identification technology. In order to precisely identify people wearing masks, we provide a deep learning algorithm based on YOLO architecture in this study. Unlike traditional CNNs, the proposed system uses a convergence layer to record numerous facial emotions while also using a number of convolutional filters to construct the faces for masked images. The presented design has numerous layers, including convolutional, max pooling, dropout, and softmax, and is both straightforward and effective. On the publicly accessible Real-World Masked Face Dataset, we assess the effectiveness of masked-faces detection (RWMFD). The investigational outcomes demonstrate an accurateness of 99.9%, demonstrating the effectiveness of our proposed methodology in classifying individuals wanting to wear facemasks. © 2022 IEEE.

Face Masked and Unmasked Humans Detection and Tracking in Video Surveillance

Due to the spread of COVID-19, people wearing face masks became a regular occurrence worldwide. Moreover, there are nations where covering one's face is done for religious or cultural reasons, or even wear face masks for convenience. However, current face detection and tracking systems are hindered by face masks as the full facial features are no longer visible and therefore became less effective. In this paper, it is proposed to improve current face detection and long-term tracking technology by extracting the facial features of the top regions of the face, taking into account the eye, eyebrow, and forehead. The methodology contains two models, the face detector and the long-term object tracker. The face detection model uses a joint dataset from ISL-UFMD and MaskedFace-Net. The dataset is used to train a Keras sequential model. The object detection model uses pre-trained YOLOv4 weights and DeepSORT to identify people and uses the tracking-by-detection method to perform long-term tracking throughout the surveillance video. The final face detection model results show a testing accuracy of 93.33% and a loss of 26.92%, which are up to par and comparable with other state-of-the-art models. © 2022 IEEE.

SWTFace: A Multi-branch Network for Masked Face Detection and Recognition

The globalization pandemic of COVID-19 has made wearing masks to become a norm in people's lives, and this preventive measure brings new challenges to face recognition algorithms. To address this problem, in this paper, a multi-branch network is proposed to simultaneously complete the task of the masked face detection and recognition. Firstly, this network improves the Swin Transformer for extraction of facial features. Secondly, a face organ attention mechanism, FOA, is proposed to make the model focus on the face organs that are not covered by masks. Then, in order to overcome the problem of inadequate masked face dataset, a data augmentation method using 3D face mesh is proposed to add face mask. Finally, the experimental results show that, compared with the benchmark model, the proposed model reduces the number of model parameters by 60.6%, while the AP of masked face recognition increases by 5.33%, which better balances speed and accuracy. © 2022 IEEE.

Masked Face Detection with Illumination Awareness

Mask mandate has been applied in many countries in the last two years as a simple but effective way to limit the Covid-19 transmission. Besides the guidance from authorities regarding mask use in public, numerous vision-based approaches have been developed to aid with the monitoring of face mask wearing. Despite promising results have been obtained, several challenges in vision-based masked face detection still remain, primarily due to the insufficient of a quality dataset covering adequate variations in lighting conditions, object scales, mask types, or occlusion levels. In this paper, we investigate the effectiveness of a lightweight masked face detection system under different lighting conditions and the possibility of enhancing its performance with the employment of an image enhancement algorithm and an illumination awareness classifier. A dataset of human subjects with and without face masks in different lighting conditions is first introduced. An illumination awareness classifier is then trained on the collected dataset, the labeling of which is processed automatically based on the difference in detection accuracy when an image enhancement algorithm is taken into account. Experimental results have shown that the combination of the masked face detection system with the illumination awareness and an image enhancement algorithm can boost the system performance to up to 8.6%, 7.4%, and 8.5% in terms of Accuracy, F1-score, and AP-M, respectively. © 2022 IEEE.

Face mask detection and classification via deep transfer learning.

Wearing a mask is an important way of preventing COVID-19 transmission and infection. German researchers found that wearing masks can effectively reduce the infection rate of COVID-19 by 40%. However, the detection of face mask-wearing in the real world is affected by factors such as light, occlusion, and multi-object. The detection effect is poor, and the wearing of cotton masks, sponge masks, scarves and other items greatly reduces the personal protection effect. Therefore, this paper proposes a new algorithm for mask detection and classification that fuses transfer learning and deep learning. Firstly, this paper proposes a new algorithm for face mask detection that integrates transfer learning and Efficient-Yolov3, using EfficientNet as the backbone feature extraction network, and choosing CIoU as the loss function to reduce the number of network parameters and improve the accuracy of mask detection. Secondly, this paper divides the mask into two categories of qualified masks (N95 masks, disposable medical masks) and unqualified masks (cotton masks, sponge masks, scarves, etc.), creates a mask classification data set, and proposes a new mask classification algorithm that the combines transfer learning and MobileNet, enhances the generalization of the model and solves the problem of small data size and easy overfitting. Experiments on the public face mask detection data set show that the proposed algorithm has a better performance than existing algorithms. In addition, experiments are performed on the created mask classification data set. The mask classification accuracy of the proposed algorithm is 97.84%, which is better than other algorithms.

Masked Face Detection and Recognition System in Real Time using YOLOv3 to combat COVID-19

A new challenge in the facial recognition technology is observed during the COVID-19 pandemic which has created a need for developing alternatives in face recognition algorithms that exist today. During this pandemic, masked faces have made face recognition applications used for security surveillance and attendance systems less effective. A comparative study was conducted on different YOLO models like YOLOv3, Tiny-YOLOv3, Tiny-YOLOv4 to judge their performances for the face detection module. From the study, it is concluded that the YOLOv3 model outperformed the other algorithms. Additionally, the face images captured from cameras were encoded and compared to determine the best face images for the face recognition module. It was identified that YOLOv3 along with face encodings from IP camera images accomplished an overall testing accuracy of 95.83% on masked and unmasked faces. The system introduced a confidence level to further reduce the error while registering the identity of the person. © 2021 IEEE.