Abstract
This paper addresses a problem of robust, accurate and fast object detection in complex environments, such as cluttered backgrounds and low-quality images. To overcome the problems with existing methods, we propose a new object detection approach, called Statistical Template Matching. It is based on generalized description of the object by a set of template regions and statistical testing of object/non-object hypotheses. A similarity measure between the image and a template is derived from the Fisher criterion. We show how to apply our method to face and facial feature detection tasks, and demonstrate its performance in some difficult cases, such as moderate variation of scale factor of the object, local image warping and distortions caused by image compression. The method is very fast; its speed is independent of the template size and depends only on the template complexity.