查看文章

The Covid-19 pandemic is a virus that has disastrous effects on human lives globally, still spreading like wildfire causing huge losses to humanity and economies. There is a need to retain some constraints for following social distancing norms, personal hygiene and wearing masks is one of the most effective ways of prevention. The proposal is to detect the face frame and confirm the proper mask covering. Using Deep Learning face detection of masks has worked tremendously, the trained system applies the processes with 4500 images, where a face is detected as masked or unmasked by using pre-trained data to conclude. The aim is to develop an algorithm to automatically detect a mask, but the approach does not facilitate the percentage of improper usage, accuracy levels are as low as 50%, if the mask is covered till mouth, the result gives an alert if not covered and can be used at traffic places and crime detection departments. The process is to locate first the region of interest in the form of a frame creating a boundary for the face, then picking a facial point detection to properly detect and then concentrate along the area of chin and nose to check the placement of the mask. Training on the input images is repeated in different epochs until the artificial face mask detection dataset is created, execution is done using TensorFlow with OpenCV and Python. Training Model Dataset used is collected from a collective set of diverse open-source datasets and images, from Kaggle's Medical Mask Dataset by Mikolaj Witkowski, Kera’s and PrajnaBhandary dataset ready for use at PyImageSearch. To simulate MobilNetV2 classifier is used to load and …