Tracking and learning graphs and pose on image sequences of faces

Abstract

We demonstrate a system capable of tracking, in real world image sequences, landmarks such as eyes, mouth or chin on a face. In the standard version, knowledge previously collected about faces is used for finding the landmarks in the first frame. In a second version, the system is able to track the face without any prior knowledge about faces and is thus applicable to other object classes. By using Gabor filters as visual features, and by both avoiding limiting assumptions and many parameters our tracking tool is simple and easy to use. As a first application the tracking results are used to estimate the pose of a face.