No abstract

An algorithm is under development, which is based on the TOD-method and predicts the characterization by human obseriers of camera-system performances. The algorithm combines the TOD-method, an early-vision model, and an orientation discriminato¡. Thi algorithm uses the same images as used in human-observer experiments. After correction for the physical properties of the display and the human eye, the algorithm tries to find the orientation of the stimulus. The utgorit¡* ca¡ aÈo predict the performance of only image processing using a simple scene-generator in stead of a camera setup.

In this paper we present a super-resolution scheme specifically designed for faces. First, a face detector is used to find faces in a video frame, after which an optical flow algorithm is applied to track feature points on the faces. Given the set of flow vectors corresponding to a single face, we propose to use the epipolar geometry for rejecting outlying flow vectors. This will improve the registration of the face over multiple frames, and thus lead to an improved super-resolution image. An iterative backprojection method is used for acquiring the super-resolution images.