TY  - EJOU
AU  - Nicolas, Shangwe Charmant 

TI  - CNN-LSTM Face Mask Recognition Approach to Curb Airborne Diseases COVID-19 as a Case
T2  - Journal of Intelligent Medicine and Healthcare

PY  - 2022
VL  - 1
IS  - 2
SN  - 2837-634X

AB  - The COVID-19 outbreak has taken a toll on humankind and the world’s health to a breaking point, causing millions of deaths and cases worldwide. Several preventive measures were put in place to counter the escalation of COVID-19. Usage of face masks has proved effective in mitigating various airborne diseases, hence immensely advocated by the WHO (World Health Organization). A compound CNN-LSTM network is developed and employed for the recognition of masked and none masked personnel in this paper. 3833 RGB images, including 1915 masked and 1918 unmasked images sampled from the Real-World Masked Face Dataset (RMFD) and the Simulated Masked Face Dataset (SMFD), plus several personally taken images using a webcam are utilized to train the suggested compound CNN-LSTM model. The CNN-LSTM approach proved effective with 99% accuracy in detecting masked individuals.
KW  - COVID-19; face mask; airborne diseases; SARS-CoV-2; CNN; LSTM

DO  - 10.32604/jimh.2022.033058