In the midst of the ongoing COVID-19
pandemic, adherence to safety measures such as wearing
masks has become crucial. To assist in enforcing maskwearing norms without relying on manual intervention,
we present a mask detection system that utilizes a
Convolutional Neural Network (CNN) and facial
recognition algorithm. Our system compares images of
faces with and without masks, automatically detects the
presence or absence of masks, and triggers an alert
mechanism for the general public.
In this report, we address the challenge of detecting
masked face regions by proposing a novel approach that
involves discarding the masked region and leveraging
deep learning-based features. By focusing on the
uncovered facial areas, our model aims to improve
accuracy and efficiency in mask detection.
Through the utilization of CNN, our system learns
discriminative features from the face images, enabling it
to accurately classify whether an individual is wearing a
mask or not. The facial recognition algorithm further
enhances the system's ability to identify and track
individuals in real-time, facilitating quick and reliable
detection.
To evaluate the effectiveness of our proposed model,
we conducted extensive experiments on a diverse dataset
containing images of individuals wearing masks. The
results demonstrate the system's high accuracy and
efficiency in detecting masks, even in challenging
scenarios such as varied lighting conditions and different
mask types.
Our mask detection system holds significant
potential for deployment in various public spaces, such as
airports, train stations, and shopping malls, to help
ensure compliance with mask-wearing guidelines. By
automating the detection process, the system can
contribute to reducing the spread of COVID-19 and
protecting public health.
Keywords :
Mask Detection, Convolutional Neural Network (CNN), Facial Recognition, COVID-19, Safety Measures