Aspects of the Detection of Scene Congruence

The problem of matching two scenes, one contained in the other, arises in many practical picture processing tasks including stereocompilation, classification of photographic data, and map matching for navigation and guidance. Because the images are not exact replicas, but rather noisy and perhaps geometrically distorted versions of the original scenes, it is necessary to develop a body of theory capable of providing answers to questions concerning effects of various types of error, and means for minimizing the effects of such errors. This paper presents a "decision space" approach to the problem for dealing with small amounts of noise and distortion, and a promising new technique for dealing with "rubber sheet" distortion.