基于半监督学习的人脸识别反欺骗方法研究

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

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。

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 an-ti-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 accu-racy.With a few labeled samples,the proposed method outperforms Improved-GAN and common semi-supervised me-thods,and surpasses supervised learning method based on support vector machine and convolutional neural network.