Face Mask Identification Using Spatial and Frequency Features in Depth Image from Time-of-Flight Camera

Abstract

Face masks can effectively prevent the spread of viruses. It is necessary to determine the wearing condition of masks in various locations, such as traffic stations, hospitals, and other places with a risk of infection. Therefore, achieving fast and accurate identification in different application scenarios is an urgent problem to be solved. Contactless mask recognition can avoid the waste of human resources and the risk of exposure. We propose a novel method for face mask recognition, which is demonstrated using the spatial and frequency features from the 3D information. A ToF camera with a simple system and robust data are used to capture the depth images. The facial contour of the depth image is extracted accurately by the designed method, which can reduce the dimension of the depth data to improve the recognition speed. Additionally, the classification process is further divided into two parts. The wearing condition of the mask is first identified by features extracted from the facial contour. The types of masks are then classified by new features extracted from the spatial and frequency curves. With appropriate thresholds and a voting method, the total recall accuracy of the proposed algorithm can achieve 96.21%. Especially, the recall accuracy for images without mask can reach 99.21%.

Advances in Silicon-Based Integrated Lidar

“…Alternatively, the light source can emit continuous waves [24,25] and we can calculate the time indirectly by measuring the phase shift of the received signal. Time of flight is applied in the deep camera to obtain more space information from the photos [26]. After the laser is emitted by the transmitter in Figure 2, it is reflected or scattered objects at different positions.…”

A Face Detection and Standardized Mask-Wearing Recognition Algorithm

“…It uses ResNet-50 [ 10 ] to extract feature maps and employs decision trees, supports vector machines and integrated algorithms for recognition, but the monitoring speed is greatly reduced while obtaining high accuracy. Wang et al [ 11 ] used the spatial and frequency features from the 3D information to detect masks. Compared with the YOLOv4 [ 12 ] algorithm, which has a high balance of accuracy and speed, it has a faster detection speed but worse detection accuracy.…”