The rapid global spread of COVID-19, officially declared a pandemic by the World Health Organization (WHO), emphasized the critical need for preventive public health measures such as wearing face masks in shared and crowded environments. Ensuring compliance through manual supervision is labor-intensive, inconsistent, and impractical in large-scale public settings. To address this challenge, this research proposes an automated Face Mask Detection system using Artificial Intelligence (AI) and Machine Learning (ML) techniques, specifically leveraging deep learning-based computer vision models for real-time monitoring. The proposed system integrates face detection and mask classification into a unified pipeline. For face localization, a deep learning-based Single Shot Detector (SSD) framework is employed, while mask classification is performed using a transfer learning approach based on MobileNetV2, a lightweight Convolutional Neural Network (CNN) architecture optimized for real-time applications. The dataset consists of labeled images categorized into three classes: properly worn mask, improperly worn mask, and no mask. Extensive preprocessing techniques, including image resizing, normalization, and data augmentation, were applied to improve model generalization and robustness. The model was trained using the Adam optimizer with categorical cross-entropy loss and evaluated using standard performance metrics such as accuracy, precision, recall, F1-score, and confusion matrix analysis. Experimental results demonstrate an overall accuracy of approximately 97–98% on the validation dataset, with real-time detection capability achieving 18–22 frames per second (FPS) on standard hardware configurations. The system shows strong performance under varying lighting conditions and multiple face detection scenarios. The proposed solution offers a scalable, cost-effective, and efficient automated monitoring system suitable for deployment in public spaces such as airports, hospitals, educational institutions, transportation hubs, and corporate offices. Furthermore, the system can be extended to integrate additional public safety features such as social distancing monitoring and crowd density estimation. This research contributes to the practical application of AI-driven surveillance systems in public health management and demonstrates the effectiveness of transfer learning-based CNN models in real-time image classification tasks.
Artificial Intelligence, Machine Learning, Deep Learning, Face Mask Detection, Convolutional Neural Networks, Transfer Learning, Computer Vision, Real-Time Surveillance.
International Journal of Trend in Scientific Research and Development - IJTSRD having
online ISSN 2456-6470. IJTSRD is a leading Open Access, Peer-Reviewed International
Journal which provides rapid publication of your research articles and aims to promote
the theory and practice along with knowledge sharing between researchers, developers,
engineers, students, and practitioners working in and around the world in many areas
like Sciences, Technology, Innovation, Engineering, Agriculture, Management and
many more and it is recommended by all Universities, review articles and short communications
in all subjects. IJTSRD running an International Journal who are proving quality
publication of peer reviewed and refereed international journals from diverse fields
that emphasizes new research, development and their applications. IJTSRD provides
an online access to exchange your research work, technical notes & surveying results
among professionals throughout the world in e-journals. IJTSRD is a fastest growing
and dynamic professional organization. The aim of this organization is to provide
access not only to world class research resources, but through its professionals
aim to bring in a significant transformation in the real of open access journals
and online publishing.