Multi-view face alignment guided by several facial feature points

This paper proposes an improved algorithm for ASM addressing at face alignment with pose variation conquering local obstruction. To providing good initialization of ASM for reliable searching starting-point and faster convergence, an affine transform insensitive initialization algorithm (ATIIA) is employed after several facial feature points are extracted by SDAM searching. Landmarks of ASM are sampled with special strategy to sufficiently describe gray-level information surrounding them. Special searching strategy is also provided for ASM so that problem of local obstruction can be solved. For multi-view face alignment, view-based ASMs are trained respectively for 5 face pose based on CMU-PIE database. The exciting experiment results are shown proving that this method is robust and not susceptible to various factors such as the scale of image, the rotation of head, the local obstruction and so on.