Face Recognition With Masks Based on Spatial Fine-Grained Frequency Domain Broadening
Ieee Access
; 10:75536-75548, 2022.
Article
in English
| Web of Science | ID: covidwho-1978318
ABSTRACT
Along with social distancing, wearing masks is an effective method of preventing the transmission of COVID-19 in the ongoing pandemic. However, masks occlude a large number of facial features, preventing facial recognition. The recognition rate of existing methods may be significantly reduced by the presence of masks. In this paper, we propose a method to effectively solve the problem of the lack of facial feature information needed to perform facial recognition on people wearing masks. The proposed approach uses image super-resolution technology to perform image preprocessing along with a deep bilinear module to improve EfficientNet. It also combines feature enhancement with frequency domain broadening, fuses the spatial features and frequency domain features of the unoccluded areas of the face, and classifies the fused features. The features of the unoccluded area are increased to improve the accuracy of recognition of masked faces. The results of a cross-validation show that the proposed approach achieved an accuracy of 98% on the RMFRD dataset, as well as a higher recognition rate and faster speed than previous methods. In addition, we also performed an experimental evaluation in an actual facial recognition system and achieved an accuracy of 99%, which demonstrates the effectiveness and practicability of the proposed method.
Face recognition; Feature extraction; Facial features; Frequency-domain; analysis; Generative adversarial networks; Image recognition; Training; Face recognition with mask; convolutional neural network; frequency; domain widening; bilinear module; RMFRD dataset; Computer Science; Engineering; Telecommunications
Full text:
Available
Collection:
Databases of international organizations
Database:
Web of Science
Language:
English
Journal:
Ieee Access
Year:
2022
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS