Localizing facial landmarks by exemplar-based graph matching (EGM).
Despite the fact that the chin area is partially occluded, EGM still accurately locates the facial landmarks. EGM first finds similar exemplars through a RANSAC step. These exemplars are then used to generate (a) candidate positions for landmarks and to learn (b) an affine-invariant shape constraint, where the position of each landmark (e.g., the chin) is modeled as a weighted linear combination of the other landmarks. By combining these two sources, EGM solves a graph matching problem to obtain (c) the optimal landmark positions.
Localizing facial landmarks (a.k.a., face alignment) is a fundamental step in facial image analysis. However, the problem is still challenging due to the large variability in pose and appearance, and the existence of occlusions in real-world face images.
We present exemplar-based graph matching (EGM) framework for facial landmark localization. Compared to conventional algorithms, EGM has three advantages:
The Helen dataset and its label used in the paper available at here.