Face mask detection using deep convolutional neural network and multi-stage image processing.

•A customized image dataset is built for research on face mask detection.•The dataset is manually labeled to provide high annotation accuracy.•For Face mask detection customized CNN with multi-step image processing is used.•The performance of the proposed CNN is compared with YOLO v3 and Faster R-CNN.•Two publicly available datasets including MAFA and MOXA used for validation.