Face Alignment Using View-Based Direct Appearance Models

摘要

Accurate face alignment is the prerequisite for many computer vision problems, such as face recognition, synthesis and 3D face modeling. In this article, a novel appearance model, called direct appearance model (DAM), is proposed and its extended view-based models are applied for multiview face alignment. Similar to the active appearance model (AAM), DAM also makes ingenious use of both shape and texture constraints; however, it does not combine them as in AAM; texture information is used directly to predict the shape and estimate the position and appearance (hence the name DAM). The way that DAM models shapes and textures has the following advantages as compared with AAM: (1) DAM subspaces include admissible appearances previously unseen in AAM, (2) it can converge more quickly and has higher accuracy, and (3) the memory requirement is cut down to a large extent. Extensive experiments are presented to evaluate the DAM alignment in comparison with AAM.