International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 183 - Number 13 |
Year of Publication: 2021 |
Authors: Shivam Sourav, Shikhar Mattoo, Chitra Nasa |
10.5120/ijca2021921445 |
Shivam Sourav, Shikhar Mattoo, Chitra Nasa . Face Mask Detection using Mobilenet Technique. International Journal of Computer Applications. 183, 13 ( Jul 2021), 36-40. DOI=10.5120/ijca2021921445
As the rise of Corona-virus has affected at least 188 countries in the world as of 2021 period [1], the outbreak has severely affected all kinds of age groups, so wearing a mask becomes utmost responsibility of the person to stop the outbreak from further spreading, but it is impossible to monitor all the people who are wearing mask and who are not. So here comes theNovel Face Mask Detector which is a high accuracy mask detector. It uses Mobile-Net, which is a high accuracy and efficient face detection mask detection. Here Mobile-Net is used for pre-processing of the image, which consists of a feature pyramid network to fuse high-level semantic information with multiple feature maps, and a novel context attention module to focus on detecting face masks. In addition, a novel cross-class object removal algorithm is used to reject predictions with low confidences and the high intersection of union. When the image is processed as array, the array is forwarded to the Mobile-Net after this, the process of max pooling is done then the array is flattenedand through the fully connected layer the output is given. As, Mobile-Net is the light-weighted neural network to be used in the mobile phones.