An original face anti-spoofing approach using partial convolutional neural network
An original face anti-spoofing approach using partial convolutional neural network
复制标题
DOI：
10.1109/ipta.2016.7821013
复制
发表时间：
2016-12
期刊：
影响因子：
--
通讯作者：
Lei Li;Xiaoyi Feng;Z. Boulkenafet;Zhaoqiang Xia;Mingming Li;A. Hadid
中科院分区：
文献类型：
--
作者：
Lei Li;Xiaoyi Feng;Z. Boulkenafet;Zhaoqiang Xia;Mingming Li;A. Hadid
近年来，深度卷积神经网络已成功应用于许多计算机视觉任务，并取得了可喜的成果。因此，一些工作已经将深度学习引入到人脸反欺骗中。然而，大多数方法只是使用最终的全连接层来区分真实的和虚假的面孔。受每个卷积核都可以看作一个部分滤波器的思想启发，我们从卷积神经网络（CNN）中提取深层部分特征来区分真实的和虚假的人脸。在我们提出的方法中，CNN首先在面部欺骗数据集上进行微调。然后利用分块主成分分析（PCA）方法对特征进行降维，避免了过拟合问题。最后，利用支持向量机（SVM）对真实的人脸、真实的人脸和假人脸进行识别。在两个公共数据库Replay-Attack和CASIA上的实验表明，与现有方法相比，该方法可以获得令人满意的结果。
Recently deep Convolutional Neural Networks have been successfully applied in many computer vision tasks and achieved promising results. So some works have introduced the deep learning into face anti-spoofing. However, most approaches just use the final fully-connected layer to distinguish the real and fake faces. Inspired by the idea of each convolutional kernel can be regarded as a part filter, we extract the deep partial features from the convolutional neural network (CNN) to distinguish the real and fake faces. In our prosed approach, the CNN is fine-tuned firstly on the face spoofing datasets. Then, the block principle component analysis (PCA) method is utilized to reduce the dimensionality of features that can avoid the over-fitting problem. Lastly, the support vector machine (SVM) is employed to distinguish the real the real and fake faces. The experiments evaluated on two public available databases, Replay-Attack and CASIA, show the proposed method can obtain satisfactory results compared to the state-of-the-art methods.