Pose-invariant 3D face recognition using half face

作者：

Highlights：

•

• A coarse-to-fine strategy is proposed to detect landmarks under pose variations.

• The strategy consists of facial geometrical structure-based search and modified FLM-based search.

• The half face matching algorithm can seamlessly handle frontal and side scans.

• Experiments show that our method has high accuracy to pose variations.

摘要

•A coarse-to-fine strategy is proposed to detect landmarks under pose variations.•The strategy consists of facial geometrical structure-based search and modified FLM-based search.•The half face matching algorithm can seamlessly handle frontal and side scans.•Experiments show that our method has high accuracy to pose variations.

论文关键词：3D face recognition,Pose variation,Facial landmark localization,Half face,Iso-geodesic stripes

论文评审过程：Received 19 June 2016, Revised 18 February 2017, Accepted 7 May 2017, Available online 12 May 2017, Version of Record 30 May 2017.

论文官网地址：https://doi.org/10.1016/j.image.2017.05.004