基于稀疏子空间迁移学习的跨域人脸表情识别  

Cross-Domain Facial Expression Recognition Based on Sparse Subspace Transfer Learning

作　　者：张雯婧 宋鹏 陈栋梁 郑文明[2] 赵力[3] ZHANG Wenjing;SONG Peng;CHEN Dongliang;ZHENG Wenming;ZHAO Li(School of Computer and Control Engineering,Yantai University,Yantai 264005,China;Key Laboratory of Child Development and Learning Science of Ministry of Education,Southeast University,Nanjing 210096,China;School of Information Science and Engineering,Southeast University,Nanjing 210096,China)

机构地区：[1]烟台大学计算机与控制工程学院,烟台264005 [2]东南大学儿童发展与学习科学教育部重点实验室,南京210096 [3]东南大学信息科学与工程学院,南京210096

出　　处：《数据采集与处理》2021年第1期113-121,共9页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金(61703360)资助项目;中央高校基本科研业务费专项资金(CDLS-2019-01)资助项目。

摘　　要：针对实际场景中人脸表情识别训练和测试数据来自不同场景从而导致识别性能显著下降的问题,提出了一种基于稀疏子空间迁移学习的跨域人脸表情识别方法。首先,引入稀疏重构的思想来获得一个共同的投影矩阵,同时对重构系数矩阵施加L2,1范数约束;其次,引入图拉普拉斯正则化项来保留数据的局部判别结构;最后,利用源域丰富的标签信息,将样本投影到一个由标签信息引导的子空间中。在3个经典人脸表情数据集中进行了实验,结果表明所提方法在人脸表情识别中优于其他几种经典的子空间迁移学习方法。In practical facial expression recognition systems,recognition rates will drop significantly when the data are collected from different scenarios. To tackle this problem,in this paper,we propose a sparse subspace transfer learning for cross-domain facial expression recognition. Firstly,inspired by the idea of sparse reconstruction,we aim to learn a common projection matrix,and impose an L2,1-norm constraint on the reconstruction coefficient matrix. Secondly,we introduce the Laplacian regularization to preserve the local discriminative structure. Lastly,by utilizing the rich label information of source domain,we tend to project the source samples into a subspace guided by the label information. We conduct extensive experiments on three popular facial expression datasets. The results show that our proposed method can outperform several state-of-the-art subspace transfer learning methods in facial expression recognition.

关 键 词：人脸表情识别 迁移学习 子空间学习 图正则 回归 

分 类 号：TN912.3[电子电信—通信与信息系统]