SSDMNV2: A real time DNN-based face mask detection system using single shot multibox detector and MobileNetV2

•Probably because of the sudden emergence of the COVID-19 pandemic, at present, there are various facial recognition technology applied to people wearing masks. Detection of face masks is an extremely challenging task for the face detectors. This is because faces with masks have varied accommodations, various degrees of obstructions, and diversified mask types. Face Mask detection models have many variations. These can be divided into several categories like Boosting-based classification, Deformable Part Model-based classification and CNN base classification.•A model named as SSDMNV2 has been proposed in this paper for face mask detection using OpenCV Deep Neural Network (DNN), TensorFlow , Keras, and MobileNetV2 architecture which is used as an image classifier. OpenCV DNN used in SSDMNV2 contains SSD with ResNet-10 as backbone and is capable of detecting faces in most orientations. While MobileNetV2 used provides for lightweight and accurate predictions for classification based on whether a mask is worn or not. SSDMNV2 performs competently in differentiating images having frontal faces with masks from images having frontal faces without masks.•The SSDMNV2 model was also compared with different pre-existing models like LeNet-5, AlexNet, VGG-16, and ResNet-50 by training them on the same dataset, and the proposed model outperforms the other models in terms of accuracy, F1 score and FPS parameter. As a result SSDMNV2 model is easy to deploy on embedded devices which is not possible with heavy models and to do real-time detection using these models that requires good computational power and which is the sole purpose of the research. Face mask detection had seen significant progress in the domains of Image processing and Computer vision, since the rise of the Covid-19 pandemic. Many face detection models have been created using several algorithms and techniques. The proposed approach in this paper uses deep learning, TensorFlow, Keras, and OpenCV to detect face masks. This model can be used for safety purposes since it is very resource efficient to deploy. The SSDMNV2 approach uses Single Shot Multibox Detector as a face detector and MobilenetV2 architecture as a framework for the classifier, which is very lightweight and can even be used in embedded devices (like NVIDIA Jetson Nano, Raspberry pi) to perform real-time mask detection. The technique deployed in this paper gives us an accuracy score of 0.9264 and an F1 score of 0.93. The dataset provided in this