Abstract

In this paper, we propose a component-based discriminative approach for face alignment without requiring initialization1 . Unlike many approaches which locally optimize in a small range, our approach searches the face shape in a large range at the component level by a discriminative search algorithm. Speci fically, a set of direction classi fiers guide the search of the configurations of facial components among multiple detected modes of facial components. The direction classi fiers are learned using a large number of aligned local patches and tremely effective and able to find very good alignment results only in a few (2 ~3) misaligned local patches from the training data. The discriminative search is ex- search iterations. As the new approach gives excellent alignment results on the commonly used datasets (e.g., AR [18], FERET [21]) created under-controlled conditions, we evaluate our approach on a more challenging dataset containing over 1,700 well-labeled facial images with a large range of variations in pose, lighting, expression, and background. The experimental results show the superi- ority of our approach on both accuracy and efficiency.