Increasing validation accuracy of a face mask detection by new deep learning model-based classification

During COVID-19, wearing a mask was globally mandated in various workplaces, departments, and offices. New deep learning convolutional neural network (CNN) based classifications were proposed to increase the validation accuracy of face detection. This work introduces model that is able recognize whether person or not. The has two stages detect mask; at first stage, Haar cascade detector used face, while second CNN as classification built from scratch. experiment applied on masked faces (MAFA) dataset with images 160x160 pixels size RGB color. achieved lower computational complexity number layers, being more reliable compared other algorithms masks. findings reveal model's reaches 97.55% 98.43% different rates values features vector dense layer, which represents layer connected deeply training. Finally, suggested enhances recognition performance parameters such precision, recall, area under curve (AUC).