Face Mask Detection Using Intel OpenVINO

As more and more COVID-19 cases are reported each day and South Africa’s lock down restrictions have been loosened, we will be seeing an increase on the number of cases due to the lack of social distancing and the usage of facial masks.

In this post, I will walk you through the processes of creating a Face Mask Detector application using pre-trained models and Intel OpenVINO toolkit with OpenCV. This application can be improved and then integrated with CCTV or other types of cameras to detect and identify people without masks in public areas such as shopping centres and etc. The application could be useful in controlling the spread of the ever-increasing COVID-19 virus.lockdown

TL;DR

This project uses pre-trained models with OpenVINO toolkit and code can be found here

The How

Using the OpenVINO async API we can improve the overall frame-rate of the application, because rather than to wait for inference to complete, the application can continue operating on the host while the CPU is busy.

This walk-through executes 2 parallel inference requests for the Face Mask Detection and Face Detection networks that run simultaneously.

Using a set of the following pre-trained models:

• face-detection-adas-0001, which is a primary detection network for finding faces.
• face-mask-detection, which is a pre-trained model for detecting a mask.

The Walk-through

Face Mask Detection application uses Deep Learning/Machine Learning to recognize if a user is not wearing a mask and issues an alert as shown in the image below.

Code walk-through

Watch the complete tutorial and code walk-through. Positive and building comments will be appreciated