Determination of pose angle of face using dynamic space warping

In this paper we consider the problem of estimating the angle of pose of a face image with respect to frontal face image. Although the pose of a person's face depend on the 3D nature of the images, we show that it is possible to derive the pose of a face even from a 2D face image. This is primarily because there are several features of the image which are constrained because of it is a face. Also the objective is only to extract the single parameter pose angle, and not to reconstruct the face image. We use the features extracted along vertical scan line of an image to derive the pose angle. Using these vertical face features the image at any given pose is matched with face features from face image with front view, which corresponds to the zero pose. The matching is accomplished using dynamic space warping which is similar to dynamic time warping (DTW) used in matching the speech spectrum of isolated word recognition. The warping path obtained using DSW can be calibrated so that from the path one can derive the pose angle. In order to obtain good/accurate estimation of the pose angle, it is useful to have the reference image at several known angles.