Densely Populated Regions Face Masks Localization and Classification Using Deep Learning Models

Abstract

Over the last year, the correct wearing of facial masks in public is still a relevant matter in the fight against the COVID-19 pandemic. A popular approach that helps regulate the situation by global researchers is building smart systems for face mask detection. Following such spirit, this paper will contribute to the literature in two main aspects:(1) We first propose a new face mask detector model using the state-of-the-art RetinaFace for face localization in populous regions and the ResNet50V1 classifier to group the faces under 3 categories: correctly-worn, incorrectly-worn and no-masks-worn.(2) In order to select the ResNet50V1 as the backbone for the final model, we also analyzed its performance in accordance with another 3 classifiers on a face mask dataset beforehand. Performance metrics from the test phase have shown that our detector achieved the best accuracy among all the works compared, with 94, 59% on one test dataset and a less satisfactory 69.6% on another due to certain characteristics of the set. The code is available at: https://github.com/barbatoz0220/ Densely-populated-FMD.git

Multiclass Mask Classification with a New Convolutional Neural Model and Its Real-Time Implementation

“…Several works have managed to detect the use of face masks, and each of them uses a different method to classify the correct use of the masks. It is very common to utilize neural network architectures already tested, for example, MobileNet [ 21 ], YOLO [ 22 , 23 , 24 ], Inception [ 25 ] or Resnet [ 26 , 27 , 28 ] each one reaching different percentages of precision and different type of classification. Other authors [ 29 , 30 , 31 ], have managed to solve the same problem with their own convolutional neural network models.…”

Comparative Study of Metaheuristic Optimization of Convolutional Neural Networks Applied to Face Mask Classification

“…Two of the most widely used subsets of artificial intelligence related to face masks are deep learning (DL) and machine learning (ML). Different works on the detection of the facial mask using pre-trained models of convolutional neural networks can be found in [5][6][7], which allowed us to observe the potential of this technique in the detection and classification of facial masks [8][9][10]. In Ref.…”

“…Encircling prey: The process of prey encircling during hunting are represented by Equations ( 4) and (5).…”