Masked face detection and selected employee access to workplaces: a step towards coronavirus prevention
By: Mandal, Sujit.
Contributor(s): Saha, Manas.
Publisher: USA Springer 2023Edition: Vol.104(6), Dec.Description: 1353-1368p.Subject(s): Humanities and Applied SciencesOnline resources: Click here In: Journal of the institution of engineers (India): Series BSummary: When the coronavirus surged to a record high, the number of employees entering an organization was restricted. It was essential to monitor the entry of selected employees with facial masks at an organization. In this work, we propose a model using CCTV (closed circuit television) camera to check whether an incoming person to an organization is wearing a facial mask or not. If so, our model further checks whether the person is genuinely a selected employee of the organization. Accordingly, the entrance to the organization is either opened or closed. A two tier convolutional neural network (CNN) is implemented here. A new technique to train CNN is designed using Haar (wavelet) classifier for object detection. The first tier CNN detects only masked facial images with an accuracy of 98.67%. The second tier CNN detects masked selected employees with an accuracy of 99%. The results obtained are better than those of contemporary works. In the future a hardware implementation of the model is suggested.Item type | Current location | Call number | Status | Date due | Barcode | Item holds |
---|---|---|---|---|---|---|
Articles Abstract Database | School of Engineering & Technology Archieval Section | Not for loan | 2024-0306 |
When the coronavirus surged to a record high, the number of employees entering an organization was restricted. It was essential to monitor the entry of selected employees with facial masks at an organization. In this work, we propose a model using CCTV (closed circuit television) camera to check whether an incoming person to an organization is wearing a facial mask or not. If so, our model further checks whether the person is genuinely a selected employee of the organization. Accordingly, the entrance to the organization is either opened or closed. A two tier convolutional neural network (CNN) is implemented here. A new technique to train CNN is designed using Haar (wavelet) classifier for object detection. The first tier CNN detects only masked facial images with an accuracy of 98.67%. The second tier CNN detects masked selected employees with an accuracy of 99%. The results obtained are better than those of contemporary works. In the future a hardware implementation of the model is suggested.
There are no comments for this item.