Occluded face recognition using low-rank regression with generalized gradient direction

作者：

Highlights：

• A hierarchical sparse and low-rank model is proposed to occluded face recognition.

• Operation is based on proposed generalized image gradient direction domain.

• Proposed model uses the hierarchical adaptive weight on the sparse part.

• Reveal the robustness of ADMM optimization to weak low-rankness problem.

• Best recognition accuracy compared to stated-of-the-art methods including CNNs.

摘要

•A hierarchical sparse and low-rank model is proposed to occluded face recognition.•Operation is based on proposed generalized image gradient direction domain.•Proposed model uses the hierarchical adaptive weight on the sparse part.•Reveal the robustness of ADMM optimization to weak low-rankness problem.•Best recognition accuracy compared to stated-of-the-art methods including CNNs.

论文关键词：Occluded face recognition,Robust sparse representation,Low-rank regression model

论文评审过程：Received 17 June 2017, Revised 10 March 2018, Accepted 20 March 2018, Available online 21 March 2018, Version of Record 1 April 2018.

论文官网地址：https://doi.org/10.1016/j.patcog.2018.03.016