A Novel Detection Framework About Conditions of Wearing Face Mask for Helping Control the Spread of COVID-19

Abstract

Properly wearing a face mask has become an effective way to limit the COVID-19 transmission. In this work, we target at detecting the fine-grained wearing state of face mask: face without mask, face with wrong mask, face with correct mask. This task has two main challenging points: 1) absence of practical datasets, and 2) small intra-class distance and large inter-class distance. For the first challenging point, we introduce a new practical dataset covering various conditions, which contains 8635 faces with different wearing status. For the second challenging point, we propose a novel detection framework about conditions of wearing face mask, named Context-Attention R-CNN, which enlarge the intra-class distance and shorten inter-class distance by extracting distinguishing features. Specifically, we first extract the multiple context feature for region proposals, and use attention module to weight these context feature from channel and spatial levels. And then, we decoupling the classification and localization branches to extract more appropriate feature for these two tasks respectively. Experiments show that the Context-Attention R-CNN achieves 84.1% mAP on our proposed dataset, outperforming Faster R-CNN by 6.8 points. Moreover, Context-Attention R-CNN still exceed some state-of-the-art single-stage detectors.

A Survey on Masked Facial Detection Methods and Datasets for Fighting Against COVID-19

“…Single-stage methods based on deep learning techniques account for the largest proportion among the methods. They include Faster R-CNN [23], [77], Context-Attention R-CNN [47], InceptionV3 [78], MobileNet [60], SSD [79], YOLO [80], YOLOv2 [42], YOLOv3 [26], [29], [50], [81], [82], YOLOv4 [31], [51], [83], [84], YOLOv5 [85]- [88], and others [11], [41], [46], [52], [89]- [94], etc. It can be clearly concluded that YOLO and its variants are used widely.…”

Mask Detection and Social Distance Identification Using Internet of Things and Faster R-CNN Algorithm

“…The technologies discussed are deep learning associated with X-ray, in vitro diagnostics (IVDs), and wearable sensors based on IoT for monitoring the COVID-19 patients. In [ 17 ], detection of the face wearing mask in the fine state has been done with context attention R-CNN technique with the help of special features for the purpose of region proposal and by dissociation of localization and classification fields. The context approach R-CNN has been found to be highly accurate.…”

Masked Face Recognition Using Deep Learning: A Review

“…Moreover, the R-CNN slowly performs a ConvNet forward pass for each object proposal without sharing computation. Zhang et al [104] proposed a context-attention R-CNN as a detection framework of wearing face masks. This framework is used to expand the intra-class distance and reduce the inter-class distance by extracting distinguishing features.…”

“…MaskTheFace [31] MaskedFace-Net [32], DCNN [33], CYCLE-GAN [34], IAMGAN [35], starGAN [36], segments [39][40][41], regularization [42], sparse rep. [43] Domain-specific models FaceNet [83], SphereFace [8], MFCosface [85], VGGFace [48], DeepID [86], LSTM-autoencoders [70], DC-SSDA [71], de-corrupt autoencoders [72], 3D autoencoder [73], pose invariant FR [77], makeup-invariant [78], DBNs [79,80], attention-aware [82], margin-aware [15] Feature extraction LBPs [44], SIFT [45], HOG [89], codebooks [90], multi-stage mask learning strategy [92], attention-aware and context-aware [93][94][95], GCN [96][97][98] Mask detection R-CNN [101], Fast R-CNN [102], Faster R-CNN [103], context-attention R-CNN [104], FCN [105], U-Net [106], FAN [109], LLE-CNNs [110], ...…”