Flexible real-time programming of a distributed transputer-based vision system

The authors describe the major aspects in their transputer-based automatic vision system (TAVS) aiming to implement a scaleable and easily reconfigurable system, in which the mapping of image processing and recognition algorithms to the hardware is facilitated by automatic code generation schemes, separating methodic design and implementation details. The paper presents the system design and underlying hardware architecture first. The authors describe the modules available for iconic image processing and feature extraction and selection. The code generation for the hierarchical statistical decision network is then described, followed by the implementation of the language π for process allocation. The various system parts were tested in an implementation of real-time wooden board inspection. For this example the authors present details on typical algorithms and how they were implemented on a maintainable and scaleable industrial system