Unveiling unmasked faces: A novel model for improved mask detection using haar cascade technique

Abstract

In response to the urgent need to enforce mask-wearing compliance during the COVID-19 pandemic, this "Face Mask Detection" project introduces a robust model for identifying individuals not wearing face masks in videos. Leveraging computer vision's Haar Cascade technique, the project achieves rapid face detection within video streams, facilitating accurate mask usage assessment. This initiative holds paramount importance due to the pivotal role of masks in curbing virus spread. The model finds practical applications in monitoring mask adherence in public settings, pinpointing potential COVID-19 hotspots through data analysis, and bolstering safety via integration into surveillance systems. By effectively addressing the intricate challenge of precise mask detection, this project makes significant contributions to public health endeavors and the mitigation of COVID-19 hazards. The proposed algorithm showcases remarkable performance across various metrics. With an impressive detection rate of 98.4%, it surpasses established methods such as CNN (91.26%), PCA+SVM (93.4%), and Adaboost (96.1%), signifying its potential to revolutionize mask detection technology.