Identity preserving face completion with generative adversarial networks

Xudong WANG; Hongquan WEI; Chao GAO; Ruiyang HUANG

doi:10.11959/j.issn.2096-109x.2018070

您当前的位置：

首页 >

文章列表页 >

Identity preserving face completion with generative adversarial networks

Papers | 更新时间：2024-06-03

- Identity preserving face completion with generative adversarial networks
- Chinese Journal of Network and Information Security Vol. 4, Issue 8, Pages: 71-76(2018)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.2096-109x.2018070
  CLC： TP393
- Online First：2018-08，
  
  Published：15 August 2018
- 稿件说明：
移动端阅览
Xudong WANG, Hongquan WEI, Chao GAO, et al. Identity preserving face completion with generative adversarial networks[J]. Chinese Journal of Network and Information Security, 2018, 4(8): 71-76.
DOI：

Xudong WANG, Hongquan WEI, Chao GAO, et al. Identity preserving face completion with generative adversarial networks[J]. Chinese Journal of Network and Information Security, 2018, 4(8): 71-76. DOI： 10.11959/j.issn.2096-109x.2018070.

摘要

人脸图像补全作为图像补全技术的一种特殊应用，在被遮挡人脸的识别、人脸修复等问题上有不可替代的作用。现有的人脸补全算法只针对补全图像的真实性，而未考虑其补全后的身份一致性。针对这一问题，设计了一种基于改进的生成式对抗网络的人脸补全算法，通过引入SN-GAN算法，提高了模型训练的稳定性，同时利用人脸识别模型对生成图像加入了身份一致性约束，经过实验证明，所提方法能够在生成高真实性图像时有效保持补全图像的身份一致。

Abstract

As a special application of image completion technology

face image completion has an irreplaceable role in the occlusion of face recognition

portrait restoration and other issues.The existing face completion algorithm only aims at complementing the authenticity of the image without considering its identity consistency after completion.A face complement algorithm based on improved generative confrontation network was designed.By introducing SN-GAN algorithm

the stability of model training was improved.At the same time

the identity recognition constraint was added to the generated image using the face recognition model.Experiments have shown that the proposed method can effectively maintain the identity of the complementary image when generating high-authenticity images.

关键词

Keywords

references

MOHAMMED U , SIMON J D P , KAUTZ J . Visio-lization:generating novel facial images [J ] . ACM Transactions on Graphics , 2009 , 28 ( 3 ):57.

DENG Y , DAI Q , ZHANG Z . Graph Laplace for occluded face completion and recognition [J ] . IEEE Trans Image Process , 2011 , 20 ( 8 ): 2329 - 2338 .

GOODFELLOW I J , POUGETABADIE J , MIRZA M , et al . Generative adversarial nets [J ] . Advances in Neural Information Processing Systems , 2014 , 3 : 2672 - 2680 .

RADFORD A , METZ L , CHINTALA S . Unsupervised representation learning with deep convolutional generative adversarial networks [J ] . Computer Science , 2015

LECUN Y , BOTTOU L , BENGIO Y , et al . Gradient-based learning applied to document recognition [J ] . Proceedings of the IEEE , 1998 , 86 ( 11 ): 2278 - 2324 .

MIYATO T , KATAOKA T , KOYAMA M , et al . Spectral normalization for generative adversarial networks [C ] // ICML Workshop on Implicit Models . 2018 .

GULRAJANI I , AHMED F , ARJOVSKY M , et al . Improved training of Wasserstein GANs [C ] // Advances in Neural Information Processing Systems . 2017 .

PATHAK D , KRAHENBUHL P , DONAHUE J , et al . Context encoders:feature learning by inpainting [C ] // IEEE Computer Vision and Pattern Recognition . 2016 : 2536 - 2544 .

ISHIKAWA H , ISHIKAWA H , ISHIKAWA H . Globally and locally consistent image completion [C ] // ACM Transactions on Graphics (TOG) . 2017 :107.

WU X , HE R , SUN Z , et al . A light CNN for deep face representation with noisy labels [J ] . IEEE Transactions on Information Forensics ＆ Security , 2017 ,( 99 ): 1 - 1 .

HUANG R , ZHANG S , LI T , et al . Beyond face rotation:global and local perception GAN for photorealistic and identity preserving frontal view synthesis [J ] . arXiv:1704.04086 , 2017 : 2458 - 2467 .

XU K , BA J , KIROS R , et al . Show,attend and tell:neural image caption generation with visual attention [J ] . Computer Science , 2015 : 2048 - 2057 .

HUANG G B , MATTAR M , BERG T , et al . Labeled faces in the wild:a database forstudying face recognition in unconstrained environments [R ] . 2007 .

HUANG G B , MATTAR M , LEE H , et al . Learning to align from scratch [C ] // Advances in Neural Information Processing Systems (NIPS) . 2012 .

YU F , KOLTUN V . Multi-scale context aggregation by dilated convolutions [J ] . arXiv preprint arXiv:1511.07122 , 2015 :

NAIR V , HINTON G E . Rectified linear units improve restricted boltzmann machines [C ] // International Conference on International Conference on Machine Learning . 2010 : 807 - 814 .

IOFFE S , SZEGEDY C . Batch normalization:accelerating deep network training by reducing internal covariate shift [J ] . arXiv:1502.03167v3 , 2015 : 448 - 456 .

LAU M M , LIM K H . Investigation of activation functions in deep belief network [C ] // 2017 2nd International Conference on Control and Robotics Engineering (ICCRE) . 2017 : 201 - 206 .

CYBENKO C . Approximation by superpositions of sigmodial function [J ] . Mathematics of Control Signals ＆ Systems , 1989 ,2.

ZHENG H , YANG Z , LIU W , et al . Improving deep neural networks using softplus units [C ] // International Joint Conference on Neural Networks . 2015 : 1 - 4 .

YANG S , LUO P , LOY C C , et al . From facial parts responses to face detection:a deep learning approach [C ] // IEEE International Conference on Computer Vision . IEEE Computer Society , 2015 : 3676 - 3684 .

HUANG J B , KANG S B , AHUJA N , et al . Image completion using planar structure guidance [J ] . ACM Transactions on Graphics , 2014 , 33 ( 4 ): 1 - 10 .

Views

1709

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multi-biometrics fusion based on dynamic weighting of characteristic signal quality

Related Author

Wenbing ZHANG

Peishun LIU

Fenghui XUE

Related Institution

College of Information Science and Engineering,Ocean University of China

Institute of International Electronic Commerce,Qingdao Huanghai University

⁰