Wearing face masks in public places has reduced the global spread of COVID-19 and other bronchi/lung diseases. This paper proposes an approach for the face detection of people from the photo with or without a facemask. This task is implemented based on the features around their eyes, ears, nose, and forehead by using the original masked and unmasked images to form a baseline for face mask detection. In this work, we have used the Caffe-MobileNetV2 model for feature extraction and image classification. First, the convolutional architecture for the fast feature embedding Caffe model is used as a face detector, and then the MobileNetV2 is used for facemask identification. Experimental results revealed that the proposed approach performed well, with an accuracy of 98.54%. The work is expected to be deployed in practical cases.