REAL-TIME FACE MASK DETECTOR

Computer Science Engineering

The COVID-19 pandemic has quickly influenced our everyday lives, disrupting commerce, and movements around the world. The wearing of a mask to cover the face has become a modern normal. In the near future, several public utility providers will be asking consumers to wear masks appropriately to make use of their facilities. Face mask identification has therefore become a key factor in helping global society. Using basic Machine Learning packages such as TensorFlow, Keras, and OpenCV, this paper offers a simpler approach to achieving this objective. The proposed method correctly recognizes the face from the image and then identifies whether or not it has a mask on it. As a surveillance task officer, a face may also be identified along with a mask in motion. On two separate datasets, the technique achieves an accuracy of up to 95.77 percent and 94.58 percent, respectively. We analyze optimum parameter values using the Sequential Convolutional Neural Network model to appropriately detect the existence of masks without overfitting.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.