Facemask Detection Using Cascade Classifier Techniques

Abstract

 The proliferation of infectious diseases has underscored the importance of preventive measures, with face mask usage emerging as a crucial strategy to mitigate airborne transmission. In this context, the integration of computer vision techniques offers a technological solution for monitoring face mask compliance. This abstract presents a study focused on the implementation of Cascade Classifier techniques for automated face mask detection. The primary objective of this study is to evaluate the efficacy of Cascade Classifier techniques in identifying individuals wearing or not wearing face masks. By leveraging machine learning algorithms and object detection principles, the study aims to develop a reliable and efficient system for real-time face mask detection.The study employs a dataset comprising diverse images of individuals in various environments, both with and without face masks. Utilizing the OpenCV library, Cascade Classifier techniques are trained to recognize distinctive patterns associated with face masks. The cascade framework's ability to perform rapid and successive filtering is leveraged to accurately detect faces and assess mask presence.The results of the study demonstrate the successful implementation of Cascade Classifier techniques for face mask detection. The trained classifier exhibits commendable accuracy, precision, and recall in distinguishing between mask-wearing and non-mask-wearing individuals. The system showcases its capability to operate in real-time scenarios, contributing to efficient monitoring of public spaces.