Fusing landmark-based features at kernel level for face recognition

作者：

Highlights：

• An improved landmark-based multi-scale LBP feature is proposed.

• A novel model is proposed to fuse LBP feature and Gabor feature at kernel-level.

• An optimization algorithm is proposed to solve the kernel-level fusing model.

摘要

Highlights•An improved landmark-based multi-scale LBP feature is proposed.•A novel model is proposed to fuse LBP feature and Gabor feature at kernel-level.•An optimization algorithm is proposed to solve the kernel-level fusing model.

论文关键词：Face recognition,Landmark-based feature,Feature fusion,Multi-kernel discriminant analysis,Face identification,Face verification

论文评审过程：Received 18 March 2016, Revised 8 September 2016, Accepted 18 October 2016, Available online 22 October 2016, Version of Record 28 October 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.10.021