TY - GEN
T1 - Lightweight Network for Masked Face Recognition Based on Improved Dual Attention Mechanism
AU - Zhang, Yilin
AU - Peng, Xiwei
AU - Guo, Yujie
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - More and more people are wearing masks to avoid contracting COVID-19. However, masked occlusion will lead to the loss of facial features. The universal face recognition model cannot recognize the masked face accurately and quickly. Masked face recognition (MFR) has become a very urgent challenge. Based on MobileNetV2, this paper will replace the average pooling in the attention module with depth-separable convolution, also the normalization operation is improved by replacing the Relu activation function with Prelu. The improved dual attention module is introduced to redistribute the weight parameters of bottleneck. The results show that the accuracy of mask-LFW and mask-AgeDB data sets reached 90% and 91% respectively, and the model size is reduced to one tenth of the other common model size. It is proved that the improved network can effectively reduce the occlusion interference, reduce the calculation amount, and improve the robustness of the system.
AB - More and more people are wearing masks to avoid contracting COVID-19. However, masked occlusion will lead to the loss of facial features. The universal face recognition model cannot recognize the masked face accurately and quickly. Masked face recognition (MFR) has become a very urgent challenge. Based on MobileNetV2, this paper will replace the average pooling in the attention module with depth-separable convolution, also the normalization operation is improved by replacing the Relu activation function with Prelu. The improved dual attention module is introduced to redistribute the weight parameters of bottleneck. The results show that the accuracy of mask-LFW and mask-AgeDB data sets reached 90% and 91% respectively, and the model size is reduced to one tenth of the other common model size. It is proved that the improved network can effectively reduce the occlusion interference, reduce the calculation amount, and improve the robustness of the system.
KW - COVID-19
KW - Improved bottleneck
KW - Improved dual attention mechanism
KW - Masked face recognition
KW - MobileNetV2
UR - http://www.scopus.com/inward/record.url?scp=85170829219&partnerID=8YFLogxK
U2 - 10.1109/ICMA57826.2023.10215964
DO - 10.1109/ICMA57826.2023.10215964
M3 - Conference contribution
AN - SCOPUS:85170829219
T3 - 2023 IEEE International Conference on Mechatronics and Automation, ICMA 2023
SP - 1621
EP - 1626
BT - 2023 IEEE International Conference on Mechatronics and Automation, ICMA 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 20th IEEE International Conference on Mechatronics and Automation, ICMA 2023
Y2 - 6 August 2023 through 9 August 2023
ER -