Hallucinating Faces

Abstract

In most surveillance scenarios there is a large distance between the camera and the objects of interest in the scene. Surveillance cameras are also usually set up with wide fields of view in order to image as much of the scene as possible. The end result is that the objects in the scene normally appear very small in surveillance imagery. It is generally possible to detect and track the objects in the scene, however, for tasks such as automatic face recognition and license plate reading, resolution enhancement techniques are often needed. Although numerous resolution enhancement algorithms have been proposed in the literature, most of them are limited by the fact that they make weak, if any, assumptions about the scene. We propose an algorithm that can be used to learn a prior on the spatial distribution of the image gradient for frontal images of faces. We proceed to show how such a prior can be incorporated into a super-resolution algorithm to yield 4-8 fold improvements in resolution (16-64 times as many pixels) using as few as 2-3 images. The additional pixels are, in effect, hallucinated. We also apply our algorithms to text data.