Year: 2019
Type: other
Abstract: We propose a deep learning network L1-2D2PCANet for face recognition, which is based on L1-norm-based two-dimensional principal component analysis (L1-2DPCA). In our network, the role of L1-2DPCA is to learn the filters of multiple convolution layers. After the convolution layers, we deploy binary hashing and blockwise histogram for pooling. We test our network on some benchmark facial datasets, including Yale, AR face database, extended Yale B, labeled faces in the wild-aligned, and Face Recognition Technology database with the convolution neural network, PCANet, 2DPCANet, and L1-PCANet as comparison. The results show that the recognition performance of L1-2D2PCANet in all tests is better than baseline networks, especially when there are outliers in the test data. Owing to the L1-norm, L1-2D2PCANet is robust to outliers and changes of the training images.
Source: Journal of Electronic Imaging
Authors: Yun-Kun Li, Xiao-Jun Wu, Josef Kittler
Institutions: Jiangnan University, University of Surrey
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
Funders: National Science Foundation, National Natural Science Foundation of China, Ministry of Education of the People's Republic of China, Higher Education Discipline Innovation Project, Defence Science and Technology Laboratory, Multidisciplinary University Research Initiative, Engineering and Physical Sciences Research Council
Awards: (N00014-16-R-FO05) Semantic Information Pursuit for Multimodal Data Analysis, G1106734755, G1474490597, Face Matching for Automatic Identity Retrieval, Recognition, Verification and Management, G283044312, G334333299, G344950217, G4770326006, G5490072873, G5661323400, G575726069, G5818953154, 稀疏低秩表示优化理论与新方法研究, G7037856708, 鉴别性稀疏编码与模糊多核学习理论及其应用研究, G764753648, G8403763664, G9000378566
OpenAlex ID: W2803171192