Salient and non-salient fiducial detection using a probabilistic graphical model

作者：

Highlights：

• The new pattern recognition method accurately detects a dense set of object landmarks in an image.

• The relative positions of pairs of landmarks are encoded by a probabilistic graph.

• Non-salient landmarks, missed by other detectors, are now robustly detected.

• It is applicable to different objects – e.g., faces, hands, and cardiac structures.

摘要

Highlights•The new pattern recognition method accurately detects a dense set of object landmarks in an image.•The relative positions of pairs of landmarks are encoded by a probabilistic graph.•Non-salient landmarks, missed by other detectors, are now robustly detected.•It is applicable to different objects – e.g., faces, hands, and cardiac structures.

论文关键词：Shape modeling,Detailed face shape detection,Face detection,Probabilistic graphical model,Landmark detection

论文评审过程：Received 6 June 2012, Revised 17 April 2013, Accepted 10 June 2013, Available online 21 June 2013.

论文官网地址：https://doi.org/10.1016/j.patcog.2013.06.013