[KSCI] Korea Science Citation Index Service

http://dx.doi.org/10.9717/kmms.2022.25.11.1582

Face Recognition Research Based on Multi-Layers Residual Unit CNN Model

Zhang, Ruyang (Dept. of Information and Communication Engineering, Graduate School, Tongmyong University)
Lee, Eung-Joo (Dept. of Information and Communication Engineering, Graduate School, Tongmyong University)

Publication Information

Journal of Korea Multimedia Society / v.25, no.11, 2022 , pp. 1582-1590 More about this Journal

Abstract

Due to the situation of the widespread of the coronavirus, which causes the problem of lack of face image data occluded by masks at recent time, in order to solve the related problems, this paper proposes a method to generate face images with masks using a combination of generative adversarial networks and spatial transformation networks based on CNN model. The system we proposed in this paper is based on the GAN, combined with multi-scale convolution kernels to extract features at different details of the human face images, and used Wasserstein divergence as the measure of the distance between real samples and synthetic samples in order to optimize Generator performance. Experiments show that the proposed method can effectively put masks on face images with high efficiency and fast reaction time and the synthesized human face images are pretty natural and real.

Keywords

Face Recognition; CNN Model; Deep Learning; Generative Adversarial Network;

Citations & Related Records

Reference

1	T. Yaniv, M. Yang, R.M. Aurelio, and L. Wolf, "Deepface: Closing the Gap to Human Level Performance in Face Verification," Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1701-1708, 2014.
2	W.K. Xu and E.J. Lee, "Human-computer Catural User Interface Based on Hand Motion Detection and Tracking," The Journal of Multimedia Information System, Vol. 15, No. 4, pp. 501-507, 2012.
3	A.R. Syafeeza, M. Khalil-Hani, S.S. Liew, and R. Bakhteri, "Convolutional Neural Network for Face Recognition with Pose and Illumination Variation," Journal of IJET 2014, Vol. 6, No. 1, pp. 44-57, 2014.
4	I. Goodfellow, J. Pouget-Abadie, M. Mirza, B Xu, David Warde-Farley, S Ozair, et al., "Generative adversarial Networks," Journal of the Communications of the ACM, Vol. 63, No. 11, pp. 139-144, 2020. DOI
5	J. Wu, Z. Huang, J. Thoma, D Acharya, and L. Van Gool, "Wasserstein Divergence for GANs," Proceedings of the European Conference on Computer Vision, pp. 653-668, 2018.
6	N. Pandey and A. Sacakis, "Poly-GAN: MultiConditioned GAN for Fashion Synthesis," Journal of Neurocomputing, Vol. 414, pp. 356-364, 2020. DOI
7	K.M. He, X.Y. Zhang, S.Q. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," arXiv Preprint, arXiv:1512. 03385, 2015.
8	Z. Liu, P. Luo, X. Wang, and X. Tang, "Deep Learning Face Attributes in the Wild," Proceedings of the IEEE International Conference on Computer Vision, pp. 3730-3738, 2015.
9	S. Florian, K. Dmitry, and J. Philbin, "Facenet: A Unified Embedding for Face Recognition and Clustering," Proceedings of 2015 IEEE Conference on Computer Vision and Patten Recognition, pp. 815-823, 2015.
10	J. Wang and E.J. Lee, "Low Resolution Rate Face Recognition Based on Multi-scale CNN," Journal of Journal of Korea Multimedia Society, Vol. 21, No. 12, pp. 1467-1472, 2018.
11	M. Jaderberg, K. Simonya, A. Zisserman, and K Kavukcuoglu, "Spatial Transformer Networks," Proceedings of the Advances in Neural Information Processing Systems, pp. 2017-2025, 2015.
12	C. Szecedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, et al., "Going Deeper with Convolutions," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-9, 2015.
13	I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A.C. Courville, "Improved Training of Wasserstein GANs," Proceedings of Advances in Nerual Information Processing Systems, pp. 5767-5777, 2017.
14	T. Miyato, T. Kataoka, M. Koyama, and Y. Yoshida, "Spectral Normalization for Generative Adversarial Networks," International Conference on Learning Representations, 2018.