Hierarchical facial landmark localization via cascaded random binary patterns

作者：

Highlights：

• A regression framework is designed for multi-view facial landmark localization.

• The use of comparison based feature is highly efficient for landmark localization.

• Gradient-boosted decision tree is superior to random forest for localization task.

• Accuracy and speed are tested on the widely used open dataset: LFW, AFLW and 300-W.

摘要

Highlights•A regression framework is designed for multi-view facial landmark localization.•The use of comparison based feature is highly efficient for landmark localization.•Gradient-boosted decision tree is superior to random forest for localization task.•Accuracy and speed are tested on the widely used open dataset: LFW, AFLW and 300-W.

论文关键词：Facial landmark localization,Random binary pattern,Hierarchical regression,Gradient boosting decision tree

论文评审过程：Received 13 September 2013, Revised 22 July 2014, Accepted 8 September 2014, Available online 18 September 2014.

论文官网地址：https://doi.org/10.1016/j.patcog.2014.09.007