基于改进神经网络的戴口罩人脸识别研究。
Research on Recognition of Faces with Masks Based on Improved Neural Network.
机构信息
The Affiliated Hospital of Qingdao University, Qingdao 266000, China.
School of Computer and Communication Engineering, China University of Petroleum (East of China), Qingdao 266000, China.
出版信息
J Healthc Eng. 2021 Nov 18;2021:5169292. doi: 10.1155/2021/5169292. eCollection 2021.
BACKGROUND
At present, the new crown virus is spreading around the world, causing all people in the world to wear masks to prevent the spread of the virus. . People with masks have found a lot of trouble for face recognition. Finding a feasible method to recognize faces wearing masks is a problem that needs to be solved urgently.
METHOD
This paper proposes a mask recognition algorithm based on improved YOLO-V4 neural network and the integrated SE-Net and DenseNet network and introduces deformable convolution.
CONCLUSION
Compared with other target detection networks, the improved YOLO-V4 neural network used in this paper improves the accuracy of face recognition and detection with masks to a certain extent.
背景
目前新冠病毒在全球范围内传播，导致全世界所有人都戴口罩以防止病毒传播。戴口罩的人给人脸识别带来了很多麻烦。找到一种可行的方法来识别戴口罩的人脸是一个亟待解决的问题。
方法
本文提出了一种基于改进的 YOLO-V4 神经网络和集成的 SE-Net 和 DenseNet 网络的口罩识别算法，并引入了可变形卷积。
结论
与其他目标检测网络相比，本文中使用的改进的 YOLO-V4 神经网络在一定程度上提高了戴口罩的人脸识别和检测的准确性。
Zotero 插件