面向低质量数据的3D人脸识别  

3D Face Recognition for Low Quality Data

作　　者：龚勋[1] 周炀 GONG Xun;ZHOU Yang(School of Information Science and Technology,Southwest Jiaotong University,Chengdu 611756)

机构地区：[1]西南交通大学信息科学与技术学院,成都611756

出　　处：《电子科技大学学报》2021年第1期43-51,共9页Journal of University of Electronic Science and Technology of China

基　　金：国家自然科学基金(61876158);四川省重点研发项目(2019YFS0432);北京航空航天大学的支持

摘　　要：该文提出了面向低质量数据的3D人脸识别方法。该方法针对快速采集设备的低质量3D人脸数据提出了空间注意力机制的Dropout(SAD)、类间正则化损失函数(IR Loss),有效提升了不完整3D人脸数据的识别精度。SAD通过空间注意力机制对特征图中权重大的部分随机Dropout,让网络学习到更多的隐藏特征;IR Loss通过约束不同身份人脸间的聚类中心的距离分离,使网络学习到的不同身份人的人脸特征相似度更低。实验表明,在当前最大规模的低质量数据集(Lock3DFace)上,该方法优于当前的基准方法,且提出的SAD和IR Loss表现出了强大的适用性和鲁棒性。For the low-quality 3D face data collected by the fast collection device,we propose a face recognition method which consists of Spatial Attention-based Dropout(SAD)and Inter-class Regularization Loss function(IR Loss).This method effectively improves the recognition accuracy of incomplete 3D face data.SAD allows the network to learn more hidden features by randomly dropping out the important parts of the feature map based on the spatial attention mechanism.And IR Loss makes the feature similarity between faces with different identities lower by restricting the distance separation of the class centers between them.Experiments show that the method proposed in this paper is superior to the current benchmark methods on a largest low-precision dataset(Lock3DFace),and the SAD and IR Loss we proposed show strong applicability and robustness.

关 键 词：3D人脸识别 损失函数 低质量3D人脸 空间注意力机制 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]