Deep Learning Technique to Detect Face Mask in the COVID-19 Pandemic Period (original) (raw)

The COVID-19 epidemic has had a fast impact on our daily lives, affecting global trade and mobility. Wearing a protective face mask is critical for lowering the chance of infection from a noxious individual during the "presymptomatic" stage and preventing viral transmission. Face mask detection has therefore become a critical job in today's global society. Face masking has become the new normal. Many public service providers will need consumers to wear masks appropriately in the near future in order to use their services. As a result, detecting face masks has become a critical duty in aiding worldwide civilization. This project demonstrates a simplified method for accomplishing this goal by combining a Deep Learning methodology known as Convolutional Neural Networks with some fundamental Machine Learning tools such as TensorFlow, Keras, and OpenCV. The suggested technique accurately recognizes the face in the picture and then determines whether or not it is covered by a mask. A cascade classifier and a pre-trained CNN with two 2D convolution layers linked to layers of dense neurons are used in the suggested approach. Here, we look at how to use the Sequential CNN model to find the best parameter values for accurately detecting the existence of masks without overfitting. The model is trained and validated before being deployed, and as a result, the approach achieves an accuracy of up to 95.77 %.

Sign up for access to the world's latest research.

checkGet notified about relevant papers

checkSave papers to use in your research

checkJoin the discussion with peers

checkTrack your impact