Efficient masked face recognition method during the COVID-19 pandemic.

Walid Hariri

doi:10.1007/s11760-021-02050-w

Abstract

The coronavirus disease (COVID-19) is an unparalleled crisis leading to a huge number of casualties and security problems. In order to reduce the spread of coronavirus, people often wear masks to protect themselves. This makes face recognition a very difficult task since certain parts of the face are hidden. A primary focus of researchers during the ongoing coronavirus pandemic is to come up with suggestions to handle this problem through rapid and efficient solutions. In this paper, we propose a reliable method based on occlusion removal and deep learning-based features in order to address the problem of the masked face recognition process. The first step is to remove the masked face region. Next, we apply three pre-trained deep Convolutional Neural Networks (CNN), namely VGG-16, AlexNet, and ResNet-50, and use them to extract deep features from the obtained regions (mostly eyes and forehead regions). The Bag-of-features paradigm is then applied to the feature maps of the last convolutional layer in order to quantize them and to get a slight representation comparing to the fully connected layer of classical CNN. Finally, Multilayer Perceptron (MLP) is applied for the classification process. Experimental results on Real-World-Masked-Face-Dataset show high recognition performance compared to other state-of-the-art methods.

Highlights

The COVID-19 can be spread through contact and contaminated surfaces; the classical biometric systems based on passwords or fingerprints are not anymore safe
Inspired by the high performance of Convolutional Neural Networks (CNN)-based methods that have strong robustness to illumination, facial expression, and facial occlusion changes, we propose in this paper an occlusion removal approach and deep CNN-based model to address the problem of masked face recognition during the COVID-19 pandemic
We present the datasets’ content and variations, the experimental results using the quantization of deep features obtained from three pre-trained models, and a comparative study with other state-of-the-arts

Summary

Introduction

The COVID-19 can be spread through contact and contaminated surfaces; the classical biometric systems based on passwords or fingerprints are not anymore safe. (4) exposing the nose region is very important in the task of face recognition since it is used for face. (3) existing face recognition methods are not efficient when wearing a mask which cannot provide the whole face image for description. To tackle these problems, we distinguish two different tasks, namely face mask recognition and masked face recognition. On the other hand, aims to recognize a face with a mask basing on the eyes and the forehead regions. We use a pre-trained deep learning-based model in order to extract features from the unmasked face regions (out of the mask region). It is worth stating that the occlusions in our case can occur in only one predictable facial region (nose and mouth regions); this can be a good guide to handle this problem efficiently

Methods

Results

Discussion

Conclusion