English

Robust Face Alignment Using a Mixture of Invariant Experts

Computer Vision and Pattern Recognition 2016-10-25 v2

Abstract

Face alignment, which is the task of finding the locations of a set of facial landmark points in an image of a face, is useful in widespread application areas. Face alignment is particularly challenging when there are large variations in pose (in-plane and out-of-plane rotations) and facial expression. To address this issue, we propose a cascade in which each stage consists of a mixture of regression experts. Each expert learns a customized regression model that is specialized to a different subset of the joint space of pose and expressions. The system is invariant to a predefined class of transformations (e.g., affine), because the input is transformed to match each expert's prototype shape before the regression is applied. We also present a method to include deformation constraints within the discriminative alignment framework, which makes our algorithm more robust. Our algorithm significantly outperforms previous methods on publicly available face alignment datasets.

Keywords

Cite

@article{arxiv.1511.04404,
  title  = {Robust Face Alignment Using a Mixture of Invariant Experts},
  author = {Oncel Tuzel and Tim K. Marks and Salil Tambe},
  journal= {arXiv preprint arXiv:1511.04404},
  year   = {2016}
}

Comments

17 pages, 6 figures

R2 v1 2026-06-22T11:44:49.229Z