Discriminative pose-free descriptors for face and object matching

作者：

Highlights：

• Two Discriminative Pose-Free descriptors, DPF-SPR and DPF-LCC are proposed.

• The approach does not require separate training for different probe viewpoints.

• Very few poses required during training, the method can generalize to unseen poses.

• Experiments illustrate effectiveness in applications like face and object recognition.

摘要

•Two Discriminative Pose-Free descriptors, DPF-SPR and DPF-LCC are proposed.•The approach does not require separate training for different probe viewpoints.•Very few poses required during training, the method can generalize to unseen poses.•Experiments illustrate effectiveness in applications like face and object recognition.

论文关键词：Face recognition,Object recognition,Pose invariant matching,Metric learning,Canonical correlation,Subspace to point representation.

论文评审过程：Received 25 July 2016, Revised 25 December 2016, Accepted 10 February 2017, Available online 17 February 2017, Version of Record 6 March 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.02.016