Face Mask and Social Distancing Detection in Marketable Places using Convolutional Neural Network Algorithm

Recently, the world has witnessed a significant shift in public health practices due to the COVID-19 pandemic. Two crucial measures to curb the spread of the virus have emerged as core strategies: face mask usage and social distancing. This research study presents a novel approach for face mask and social distancing detection using Convolutional Neural Networks (CNNs). CNNs have shown great success in visual recognition tasks, making them an ideal choice for this application. The proposed system utilizes live video feeds or recorded footage and applies a series of image-processing techniques to identify and track human faces. Subsequently, a CNN is employed to classify whether individuals are wearing face masks or not, and to determine the level of adherence to social distancing guidelines. The trained neural network is capable of providing real-time feedback, aiding in monitoring and enforcing public health protocols. The system's effectiveness is evaluated using a variety of datasets, encompassing diverse demographics and environmental conditions. Results demonstrate high accuracy and reliability in both face mask detection and social distancing assessment, even in challenging scenarios with partial facial occlusion or crowded environments. Implementing such an automated system can significantly assist authorities in ensuring compliance with preventive measures and can contribute to minimizing the transmission of respiratory diseases in public spaces. Face mask detection and social distancing monitoring using CNNs present a promising solution for the ongoing battle against the COVID-19 pandemic.