We proposed an automated smart framework for screening persons who are not using a face mask. In the smart city, all public places are monitored by cameras. The cameras are used to capture images or Real-time video streams from public places, then these images are fed into a system that identifies if any person without a face mask appears in the image. If any person without a face mask is detected then this can generate a real-time alert.
Background of the System:
This proposed model showed major improvements when compared to some previous models that gave wrong predictions whenever a rider wears clothes over their face. They achieved an overall accuracy of 98% when tested.
Numerous researchers have committed efforts to designing efficient algorithms for face detection and recognition but there exists an essential difference between ‘detection of the face under mask’ and ‘detection of mask over face’. As per available literature, very little body of research is attempted to detect masks over the face. The dataset covers various face images including faces with masks, faces without masks, faces with and without masks in one image, and confusing images without masks. With an extensive dataset containing 45,000 images, our technique achieves outstanding accuracy of 98.2%
Objectives of the System
- Detect COVID-19 facemasks in images
- Detect facemasks in the real-time video stream
- Generate alarm for those people who are not wearing a mask
Significance of the System
- Our work aims to a developing technology that can accurately detect masks over the face in public areas (such as airports. railway stations, crowded markets, bus stops, etc.) to curtail the spread of Coronavirus and thereby contribute to the public healthcare.
- The proposed model requires less memory, making it easily deployable for embedded devices used for surveillance purposes. It is very difficult to monitor people manually in these areas. In this paper, a transfer learning model is proposed to automate the process of identifying the people who are not wearing masks.
It has fast and high accuracy
This system can be implemented in ATMs, Banks, etc.
Product Scope
Our goal is to train a custom deep learning model to detect whether a person is or is not wearing a mask. There exists an essential difference between ‘detection of the face under mask’ and ‘detection of mask over face’. The dataset covers various face images including faces with masks, faces without masks, faces with and without masks in one image, and confusing images without masks. This can lead to more accurate detection of the facemask and can help to control the problem of the loss of specialized physicians in isolated villages.
Operating Environment
- Our project is a working detection system and an Android App
- Operating System: Windows
- Hardware: Camera
- Database: MySQL
- Languages: Python / JavaScript / HTML
