Double linear regressions for single labeled image per person face recognition
作者：
Highlights：
• DLR seeks the best discriminating subspace and preserves the sparse structure.
• DLR uses label information to learn a more discriminative sparse structure.
• Sparse coefficient vector is quickly computed by class specific linear regression.
• The difficulty of selecting graph construction parameters is avoided in DLR.
• Promising experimental results on three public face datasets are presented.
摘要
•DLR seeks the best discriminating subspace and preserves the sparse structure.•DLR uses label information to learn a more discriminative sparse structure.•Sparse coefficient vector is quickly computed by class specific linear regression.•The difficulty of selecting graph construction parameters is avoided in DLR.•Promising experimental results on three public face datasets are presented.
论文关键词：Semi-supervised dimensionality reduction,Label propagation,Sparse representation,Linear regressions,Linear discriminant analysis,Face recognition
论文评审过程：Received 12 March 2013, Revised 10 September 2013, Accepted 19 September 2013, Available online 9 October 2013.
论文官网地址：https://doi.org/10.1016/j.patcog.2013.09.013
