基于ArcFace损失函数的人脸识别校园门禁

胡 登峰, 李 丹
四川大学锦城学院

摘要

在当今的社会中，人们已经越来越关注和重视校园安全问题。其中校园门禁系统能很好保障校园安全。本文针对目前的校园门禁系统传统形式，提出基于ArcFace损失函数的人脸识别校园门禁系统，并介绍、分析、比较不同的人脸识别中的损失函数，在CASIA-FaceV5数据集上达到了97.1%准确率，并在MXNet深度学习框架下完成了使用摄像头的人脸识别校园门禁基本原型，验证了本文提出的基于ArcFace损失函数的人脸识别校园门禁的高准确率和有效性。

关键词

ArcFace；损失函数；人脸识别；校园安全；门禁系统；特征提取

参考

[1] F. Wang, W. Liu, H. Liu, and J. Cheng. Additive margin softmax for face verification. IEEE Signal Processing Letters, 2018.

[2] Liu W Y, Wen Y D, Yu Z D, et al. SphereFace: deep hypersphere embedding for face recognition[C] ∥ 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 2017: 6738-6746.

[3] Wang H, Wang Y, Zhou Z, et al. Cosface: large margin cosine loss for deep face recognition[C]// The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June18-23, 2018, Salt Lake City, UT, USA.New York: IEEE, 2018: 5265-5274.

[4] Deng J, Guo J, Xue N, Zafeiriou S. ArcFace: additive angular margin loss for deep face recognition[C]// The IEEE Conference on Computer Vision and Pattern Recognition (CVPR),June15-20, 2019, Long Beach, CA, USA. New York: IEEE, 2019: 4690-4699.

[5] Zhang K P, Zhang Z P, Li Z F, et al. Joint face detection and alignment using multitask cascaded convolutional networks[J]. IEEE Signal Processing Letters, 2016, 23(10): 1499-1503.

[6] 顾岩 . 基于深度学习的人脸识别技术及在油田作业区的应用 研究 [D]. 成都 : 电子科技大学 , 2019.

[7] A. Krizhevsky, I. Sutskever, G. E. Hinton. Imagenet classification with deep convolutional neural networks[C]. Advances in neural information processing systems, Lake Tahoe, USA, 2012, 1097- 1105.

[8] K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint:1409.1556, 2014.

[9] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. Going deeper with convolutions. In CVPR, 2015,1.

[10] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In CVPR, 2016.