Facial Point Detection with Occlusion Insensitive Visibility-Aware Part Model

Abstract

In this paper, we describe a method named visibility-aware part model for facial point detection in static images based on the pictorial structure model. A binary part visibility term is introduced to describe the occlusion state of each part, which can determine which facial points are occluded. The introduction of the term enhances the representation power of the model especially for the occlusions. The combining of the structure constrains and the powerful appearance model makes the model more robust and reduces the possibility of model crashing in some extent. Experimental results show that our proposed model can detect facial feature points accurately and robustly under occlusions.