Face Alignment Assisted by Head Pose Estimation

Heng Yang, Wenxuan Mou, Yichi Zhang, Ioannis Patras, Hatice Gunes and Peter Robinson

Abstract

In this paper we present a supervised initialisation scheme for cascaded face alignment based on explicit head pose estimation. We first investigate the failure cases of most state of the art face alignment approaches and observe that these failures often share one common global property, i.e. the head pose variation is usually large. Inspired by this, we propose a deep convolutional network model for reliable and accurate head pose estimation. Instead of using a mean face shape, or randomly selected shapes for cascaded face alignment initialisation, we propose two schemes for generating initialisation: the first one relies on projecting a mean 3D face shape (represented by 3D facial landmarks) onto 2D image under the estimated head pose; the second one searches nearest neighbour shapes from a training set according to head pose distance. By doing so, the initialisation gets closer to the actual shape, which enhances the possibility of convergence and in turn improves the face alignment performance. We demonstrate the proposed method on the benchmark 300W dataset and show very competitive performance in both head pose estimation and face alignment.

Session

Poster 2

Files

Extended Abstract (PDF, 5M)
Paper (PDF, 5M)

DOI

10.5244/C.29.130
https://dx.doi.org/10.5244/C.29.130

Citation

Bibtex

@inproceedings{BMVC2015_130,
	title={Face Alignment Assisted by Head Pose Estimation},
	author={Heng Yang and Wenxuan Mou and Yichi Zhang and Ioannis  Patras and Hatice Gunes and Peter Robinson},
	year={2015},
	month={September},
	pages={130.1-130.13},
	articleno={130},
	numpages={13},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.130},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.130}
}