Robust Face Alignment Using a Mixture of Invariant Experts
This work addresses robust face alignment for applications like facial recognition, but it appears incremental as it builds on existing discriminative alignment frameworks with specialized experts.
The authors tackled the problem of face alignment under large variations in pose and expression by proposing a cascade of mixture of regression experts, each specialized to different subsets of pose and expression spaces, with invariance to transformations and deformation constraints. Their algorithm significantly outperformed previous methods on public datasets.
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.