In recent decades, the identification of faces with and without masks from visual data, such as video and still images, has become a captivating research subject. This is primarily due to the global spread of the Corona pandemic, which has altered the appearance of the world and necessitated the use of masks as a vital measure for epidemic prevention. Intellectual development based on artificial intelligence and computers plays a decisive role in the issue of epidemic safety, as the topic of facial recognition and identifying individuals who wear masks or not was most prominent in the introduction and in-depth education. This research proposes the creation of an advanced system capable of accurately identifying faces, both with and without masks. The suggested system incorporates a multi-layer neural network (CNN) and a gray-level co-occurrence matrix (GLCM). It also uses techniques for preparing and preprocessing data. These additions aim to enhance the efficiency and accuracy of the system's identification algorithm. The YOLO5 neural network algorithm was utilized in the post-processing phase, with the addition of a new layer consisting of six phases. We formed this layer by integrating two algorithms, GLCM and CNN. The algorithm has become effective for real-time object recognition. The obtained accuracy results showed that the proposed system successfully combined the face mask (0.975) and face datasets. (0.925).