Adaptive noise dictionary construction via IRRPCA for face recognition

作者：

Highlights：

• A novel noise dictionary for regression is developed.

• The noise dictionary is adaptive to different kinds of noise.

• Iteratively Reweighted Robust Principal Component Analysis is developed.

• Augmented Lagrangian Multiplier method is used to solve our model.

• An extended version is provided to deal with misaligned images.

摘要

•A novel noise dictionary for regression is developed.•The noise dictionary is adaptive to different kinds of noise.•Iteratively Reweighted Robust Principal Component Analysis is developed.•Augmented Lagrangian Multiplier method is used to solve our model.•An extended version is provided to deal with misaligned images.

论文关键词：Face recognition,Robust regression,Noise dictionary,Robust principal component analysis

论文评审过程：Received 13 June 2015, Revised 26 January 2016, Accepted 4 February 2016, Available online 15 February 2016, Version of Record 23 August 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.02.005