ON MACHINE VISION AND CAST

Building machines that “see” is a complex systems engineering task. While, at present, universal vision machines (with performance comparable to the human visual system) appear to be impractical, special purpose machines have been devised successfully to operate in restricted application domains. Designing such a dedicated system usually requires detailed knowledge of the application domain, experience with available processing techniques, and a large experimentation effort. Despite the peculiarities of different vision domains, many of them share similar processing techniques. We propose to develop computerized tools to support the development of application-specific vision systems in order to make this process less time-consuming and costly. We discuss some of the fundamental problems of machine vision and examine why current computer-aided systems theory (CAST) technology is not sufficient for this task. On the other hand it seems likely that developments in the Held of machine vision could have a sign...