Despite a decline in global COVID-19 cases, the persisting threat of SARS-CoV-2 coupled with waning public awareness of the virus threat has raised concerns. A notable number of individuals disregard mask usage or do so incorrectly. It is particularly concerning given that COVID-19 has high transmissibility, especially in crowded areas like shopping centers. Enforcement officers often face challenges in identifying those wearing masks improperly. Herein lies the significance of automated mask detection to aid enforcement officers in containing the spread of the virus. Hence, this paper aims to highlight the importance of automated mask detection in combatting COVID-19 transmission. Previous mask detection algorithms were intricate because they relied heavily on resource-intensive machine learning algorithms and libraries. These algorithms, however, failed to address the problem of incorrect mask usage adequately. Therefore, despite the apparent usage of masks, the virus managed to find transmission pathways. In contrast, this research focuses on creating algorithms that pinpoint improper mask usage and optimize resource utilization without compromising detection quality. The Haar cascade algorithm was utilized to detect faces and the support vector machine (SVM) was used to train the dataset. The model attained an average accuracy of 95.8%, precision of 99.7%, recall of 92.3%, and F1-score of 93.7%. The metrics aligned with prior studies, affirming their reliability. Nevertheless, limitations exist as the model faces challenges in detecting obscured facial features, requiring further research to enhance its detection capabilities. This research contributes to ongoing efforts to improve mask detection technology for more effective virus containment.