A Combination Approach for Masked Face Recognition Based on Deep Learning
Jamal M. Alrikabi, Kadhim Hasen Alibraheemi · Lixue jinzhan · 2021
Face recognition (FR) is widely applied in biometrics and it is an essential part of a biometric security system that can be run faster than other security methods and can be performed remotely. FR systems have recently achieved encouraging results using deep learning, especially using Convolutional Neural Networks (CNN). FR systems face many challenges in unconstrained environments that reduce their accuracy, the last of these challenges is the Coronavirus Disease (COVID-19), where people are forced to wear a medical mask for protection, and this makes the current face recognition system ineffective, as important parts of the face such as the nose, mouth, and chin which otherwise contributes significantly to the face recognition process are covered with a medical mask. In this study, a deep learning-based feature combination has been proposed for Masked Face Recognition (MFR). The scheme performs feature-level combination by applying two pretrained CNN models as deep feature extractors, taking into consideration the CNN architectures that have yet achieved the highest results in the ImageNet Challenge. Pretrained CNN architectures were utilized for an image-based masked face biometric system by two strategies. In the first strategy, pretrained GoogLeNet and VGGNet models were utilized to extract deep features separately, followed by a multiclass Support Vector Machine (SVM) classifier. In the second strategy, a feature-level combination was used between two feature vectors extracted by pretrained GoogLeNet and VGGNet models followed by a multiclass SVM classifier. The proposed system is implemented by using MATLAB 2020b, and to evaluate the performance of the proposed approaches, recognition accuracy is used as an evaluation metric. Three experiments were conducted using three masked face datasets which showed the efficacy of the proposed approaches. Additionally, the combination approach between two CNN-based models improves performance. The combination strategy, in particular, yields accuracy in the range of 94.62% to 95.33% on all datasets. The proposed system was compared to existing models and the findings showed that the proposed system outperformed most current models in terms of accuracy.