智能科学与技术学报 ›› 2021, Vol. 3 ›› Issue (3): 370-380.doi: 10.11959/j.issn.2096-6652.202138

• 专刊:目标智能检测与识别 • 上一篇    

基于半监督学习的人脸识别反欺骗方法研究

李莉, 曾伟良, 黄永慧, 孙为军   

  1. 广东工业大学自动化学院,广东 广州 510006
  • 修回日期:2021-08-07 出版日期:2021-09-01 发布日期:2021-09-01
  • 作者简介:李莉(1993− ),女,广东工业大学自动化学院研究助理,主要研究方向为人工智能、图像处理
    曾伟良(1986− ),男,博士,广东工业大学自动化学院副教授,主要研究方向为人工智能和物联网系统
    黄永慧(1975− )女,广东工业大学自动化学院讲师,主要研究方向为数据科学
    孙为军(1975− ),男,博士,广东工业大学自动化学院副教授,主要研究方向为人工智能和工业互联网系统
  • 基金资助:
    国家自然科学基金资助项目(61803100);广东省重点领域研发计划资助项目(2019B010118001)

Research on anti-spoofing method of face recognition based on semi-supervised learning

Li LI, Weiliang ZENG, Yonghui HUANG, Weijun SUN   

  1. School of Automation, Guangdong University of Technology, Guangzhou 510006, China
  • Revised:2021-08-07 Online:2021-09-01 Published:2021-09-01
  • Supported by:
    The National Natural Science Foundation of China(61803100);Key-Area Research and Development Program of Guangdong Province(2019B010118001)

摘要:

鉴别图像中的真伪人脸是一个长期具有挑战性的问题。当合成的伪造人脸十分逼真时,机器识别难分真假,甚至肉眼也难以区分。基于监督学习的真伪人脸识别建模往往需要大量的标签样本,模型的性能严重依赖样本的规模。提出一种基于半监督学习的人脸识别反欺骗方法,以减少对大量标签样本的依赖。该方法利用图像修复模型来学习人脸图像潜在的数据分布。在训练过程中,少量标签样本周期性地提供有监督信号来训练分类器,以区分真伪人脸。该方法可用于不同场景的伪造人脸,如基于摄像头拍摄的人脸或生成对抗网络生成的人脸。在NUAA 数据集和口罩遮挡人脸数据集 RMFD 上进行验证,实验结果表明,所提方法能够在不降低修复图像质量的情况下达到理想的分类精度。仅依靠少量带标签图像,所提方法比Improved-GAN方法和常用的半监督机器学习方法优势更明显,并优于支持向量机和卷积神经网络的监督学习方法。

关键词: 人脸反欺骗, 半监督学习, 生成对抗网络, 图像修复

Abstract:

It is a long-term challenge to identify the real and fake faces in the images.When the synthetic fake faces are very realistic, it is difficult for machines and even naked eyes to distinguish the real and fake ones.The supervised anti-spoofing method often requires a large number of labeled samples for a good performance.An anti-spoofing method of face recognition based on semi-supervised learning was proposed to reduce the dependence on massive labeled samples.The method adopted an image inpainting model to learn the data distribution of face images.During the training process, a few labeled samples periodically provided supervised signals to train the classifier to distinguish real faces from fake ones.The proposed method could be used for face anti-spoofing in different scenario, such as faces captured by cameras or generated by generative adversarial net.Accordingly, it was evaluated on the NUAA and RMFD datasets.Experiment results show that the proposed method can keep the quality of restored images, and achieve desirable classification accuracy.With a few labeled samples, the proposed method outperforms Improved-GAN and common semi-supervised methods, and surpasses supervised learning method based on support vector machine and convolutional neural network.

Key words: face anti-spoofing, semi-supervised learning, generative adversarial network, image inpainting

中图分类号: 

No Suggested Reading articles found!