<![CDATA[The use of face masks has become an essential health protocol to prevent the spread of infectious diseases. However, public compliance remains low due to the absence of effective automated monitoring systems. This study aims to develop a real-time face mask detection system using transfer learning with the InceptionV3 architecture. The model was trained on facial image datasets classified into two categories: mask and no mask. By leveraging the ability of InceptionV3 to extract complex visual features, the training process becomes more efficient without training the model from scratch. The system is integrated with a webcam to perform real-time detection in real environments. The testing results indicate that the model achieved an accuracy of 98.7%, with stable detection performance and real-time responsiveness. These findings highlight the strong potential of deep learning approaches to support automated and effective monitoring of public health protocol compliance.]]>
Copyrights © 2025
