Feature learning via partial differential equation with applications to face recognition

作者：

Highlights：

• A novel Partial Differential Equation method is proposed for feature learning.

• The feature is discriminative and invariant under rotation, translation and illumination.

• The method is efficient in low-resolution images and when the samples are few.

• To our best knowledge, this is the first work that applies PDE to feature learning.

摘要

•A novel Partial Differential Equation method is proposed for feature learning.•The feature is discriminative and invariant under rotation, translation and illumination.•The method is efficient in low-resolution images and when the samples are few.•To our best knowledge, this is the first work that applies PDE to feature learning.

论文关键词：Feature learning,Partial differential equation,Fface recognition

论文评审过程：Received 19 January 2016, Revised 27 March 2017, Accepted 28 March 2017, Available online 30 March 2017, Version of Record 8 April 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.03.034