Published Paper Details:

The COVID-19 pandemic has underscored the critical importance of wearing face masks to curb the spread of the virus, especially in densely populated areas like public transportation, industrial facilities, and other crowded spaces. However, monitoring large populations to ensure compliance with mask mandates poses significant challenges for authorities. This paper introduces a Face Mask Detection System that leverages computer vision and deep learning techniques to automate the identification of individuals wearing or not wearing masks. The system utilizes a Convolutional Neural Network (CNN) architecture, built with popular frameworks such as TensorFlow, Keras, and OpenCV, to process image data and detect masks in real-time. By training the model on datasets of masked and unmasked faces, it achieves high accuracy in distinguishing between the two categories, even in dynamic environments. The system processes live video streams from webcams, efficiently detecting mask compliance in high-traffic areas like airports, shopping malls, and offices. Designed to function under diverse lighting conditions, the system is adaptable for various deployment scenarios. Its ability to provide real-time video feed analysis makes it a valuable tool for public health authorities to monitor mask-wearing behavior, reducing the need for manual surveillance. By offering a scalable, automated solution, this system significantly aids in ensuring compliance with mask regulations, thereby supporting efforts to limit virus transmission and enhance public safety during pandemics.