Multi-directional local gradient descriptor: A new feature descriptor for face recognition

作者：

Highlights：

• A MLGD is effective in addressing problems associated with FR systems.

• The technique exploits texture information of face images in multiple directions.

• The technique has achieved superior performance on AR and LFW datasets.

• The MLGD shows improved performance compared to some of the local descriptors.

摘要

•A MLGD is effective in addressing problems associated with FR systems.•The technique exploits texture information of face images in multiple directions.•The technique has achieved superior performance on AR and LFW datasets.•The MLGD shows improved performance compared to some of the local descriptors.

论文关键词：Gradient features,Face representation,Symbolic data objects,Viola-Jones,Binary pattern

论文评审过程：Received 2 May 2018, Revised 19 November 2018, Accepted 6 February 2019, Available online 14 February 2019, Version of Record 30 March 2019.

论文官网地址：https://doi.org/10.1016/j.imavis.2019.02.001