arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.14743cs.CVcs.CG
收藏

多通道深度3D人脸识别

Multi-channel Deep 3D Face Recognition

Center for Advanced Computer Studies(高级计算机研究中心);School of Computing and Informatics(计算与信息学院);University of Louisiana at Lafayette(路易斯安那大学拉斐特分校)

Zhiqian You, Tingting Yang, Miao Jin

摘要:

人脸识别作为一种生物识别技术,以其高通量、方便性和非侵入性在许多应用中具有重要意义。深度卷积神经网络(CNN)架构的最新进展已经显著提升了基于二维(2D)面部纹理图像的面部识别的性能,并且优于使用传统方法的先前技术状态。然而,2D人脸识别的准确性仍然受到姿态,光照,化妆和表情变化的挑战。另一方面,三维(3D)人脸数据中包含的几何信息有可能克服2D人脸数据的基本限制。我们提出了一种基于3D人脸数据的多通道深度3D人脸网络用于人脸识别。我们基于3D人脸的分段线性三角网格结构计算其几何信息,然后将几何信息与颜色一起从3D平面保形展平到2D平面,以利用最先进的深度CNN架构。我们修改了网络的输入层,使其使用九个通道而不是三个通道拍摄图像,以便可以显式地向其提供更多的几何信息。我们使用VGG-Face \cite{Parkhi2015}中的图像对网络进行预训练,然后使用生成的多通道人脸图像对其进行微调。多通道深度3D人脸网络的人脸识别准确率达到了98.6。实验结果也清楚地表明,该网络的性能更好时,一个9通道的图像被展平到平面的基础上的共形映射相比,正交投影。

英文摘要:

Face recognition has been of great importance in many applications as a biometric for its throughput, convenience, and non-invasiveness. Recent advancements in deep Convolutional Neural Network (CNN) architectures have boosted significantly the performance of face recognition based on two-dimensional (2D) facial texture images and outperformed the previous state of the art using conventional methods. However, the accuracy of 2D face recognition is still challenged by the change of pose, illumination, make-up, and expression. On the other hand, the geometric information contained in three-dimensional (3D) face data has the potential to overcome the fundamental limitations of 2D face data. We propose a multi-Channel deep 3D face network for face recognition based on 3D face data. We compute the geometric information of a 3D face based on its piecewise-linear triangular mesh structure and then conformally flatten geometric information along with the color from 3D to 2D plane to leverage the state-of-the-art deep CNN architectures. We modify the input layer of the network to take images with nine channels instead of three only such that more geometric information can be explicitly fed to it. We pre-train the network using images from the VGG-Face \cite{Parkhi2015} and then fine-tune it with the generated multi-channel face images. The face recognition accuracy of the multi-Channel deep 3D face network has achieved 98.6. The experimental results also clearly show that the network performs much better when a 9-channel image is flattened to plane based on the conformal map compared with the orthographic projection.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑