Multi-Pose and Occluded Facial Landmark Localization Via Sparse Shape Representation

Automatic facial landmark localization is a challenging problem for real world images because of face pose variations and occlusions. This paper proposes a unified framework to robustly locate facial landmarks under different poses and occlusions. Instead of explicitly modeling the statistical point distribution, we use a sparse linear combination to approximate the observed shape, and hence alleviate the multi-pose problem. In addition, we use the sparsity constraint to handle outliers caused by occlusions. We also model the initial misalignment and use convex optimization techniques to solve them simultaneously and efficiently. We evaluated the proposed method extensively on both synthetic and real data. The experimental results are promising on handling pose variations and occlusions.