Binarized features with discriminant manifold filters for robust single-sample face recognition

作者：

Highlights：

•

• We propose a novel method for constructing local histogram based facial image descriptors.

• We integrate the discriminant manifold learning with local binarized features to get a new face representation.

• Our method includes training projection filters, binarizing the filter response, and extracting a descriptor.

摘要

•We propose a novel method for constructing local histogram based facial image descriptors.•We integrate the discriminant manifold learning with local binarized features to get a new face representation.•Our method includes training projection filters, binarizing the filter response, and extracting a descriptor.

论文关键词：Face recognition,Discriminant manifold filters,Local patterns,Single training sample per person

论文评审过程：Received 7 October 2017, Revised 3 March 2018, Accepted 5 March 2018, Available online 13 March 2018, Version of Record 27 March 2018.

论文官网地址：https://doi.org/10.1016/j.image.2018.03.003