Face Mask Identification Using Spatial and Frequency Features in Depth Image from Time-of-Flight Camera
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 s...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/3/1596 |
| _version_ | 1797623172114153472 |
|---|---|
| author | Xiaoyan Wang Tianxu Xu Dong An Lei Sun Qiang Wang Zhongqi Pan Yang Yue |
| author_facet | Xiaoyan Wang Tianxu Xu Dong An Lei Sun Qiang Wang Zhongqi Pan Yang Yue |
| author_sort | Xiaoyan Wang |
| collection | DOAJ |
| description | 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%. |
| first_indexed | 2024-03-11T09:24:58Z |
| format | Article |
| id | doaj.art-2815905deae1465e9ed765d42d3121fe |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T09:24:58Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-2815905deae1465e9ed765d42d3121fe2023-11-16T18:03:22ZengMDPI AGSensors1424-82202023-02-01233159610.3390/s23031596Face Mask Identification Using Spatial and Frequency Features in Depth Image from Time-of-Flight CameraXiaoyan Wang0Tianxu Xu1Dong An2Lei Sun3Qiang Wang4Zhongqi Pan5Yang Yue6Institute of Modern Optics, Nankai University, Tianjin 300350, ChinaNational Center for International Joint Research of Electronic Materials and Systems, School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, ChinaInstitute of Modern Optics, Nankai University, Tianjin 300350, ChinaShphotonics, LLC, Tianjin 300450, ChinaAngle AI (Tianjin) Technology Co., Ltd., Tianjin 300450, ChinaDepartment of Electrical & Computer Engineering, University of Louisiana at Lafayette, Lafayette, LA 70504, USASchool of Information and Communications Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaFace 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%.https://www.mdpi.com/1424-8220/23/3/15963D data processingdepth cameraface mask identification |
| spellingShingle | Xiaoyan Wang Tianxu Xu Dong An Lei Sun Qiang Wang Zhongqi Pan Yang Yue Face Mask Identification Using Spatial and Frequency Features in Depth Image from Time-of-Flight Camera Sensors 3D data processing depth camera face mask identification |
| title | Face Mask Identification Using Spatial and Frequency Features in Depth Image from Time-of-Flight Camera |
| title_full | Face Mask Identification Using Spatial and Frequency Features in Depth Image from Time-of-Flight Camera |
| title_fullStr | Face Mask Identification Using Spatial and Frequency Features in Depth Image from Time-of-Flight Camera |
| title_full_unstemmed | Face Mask Identification Using Spatial and Frequency Features in Depth Image from Time-of-Flight Camera |
| title_short | Face Mask Identification Using Spatial and Frequency Features in Depth Image from Time-of-Flight Camera |
| title_sort | face mask identification using spatial and frequency features in depth image from time of flight camera |
| topic | 3D data processing depth camera face mask identification |
| url | https://www.mdpi.com/1424-8220/23/3/1596 |
| work_keys_str_mv | AT xiaoyanwang facemaskidentificationusingspatialandfrequencyfeaturesindepthimagefromtimeofflightcamera AT tianxuxu facemaskidentificationusingspatialandfrequencyfeaturesindepthimagefromtimeofflightcamera AT dongan facemaskidentificationusingspatialandfrequencyfeaturesindepthimagefromtimeofflightcamera AT leisun facemaskidentificationusingspatialandfrequencyfeaturesindepthimagefromtimeofflightcamera AT qiangwang facemaskidentificationusingspatialandfrequencyfeaturesindepthimagefromtimeofflightcamera AT zhongqipan facemaskidentificationusingspatialandfrequencyfeaturesindepthimagefromtimeofflightcamera AT yangyue facemaskidentificationusingspatialandfrequencyfeaturesindepthimagefromtimeofflightcamera |