A Flexible Concept for Automatic Visual Inspection

This work aims to show a systematic automated visual inspection concept that speeds up the development of such systems by providing a software reuse and setup concept. A new, highly adaptable concept for visual inspection separates the detection of primitives from the modelbased analysis process. This separation is reached by defining a general analysis graph for inspection, containing detail relations that represent detection algorithms. Together with an object specific description, defined in a so called description language, the analysis graph is instantiated. Existing pattern recognition software is re-used in the detection stage and therefore the use of any detection algorithm is possible without changing the analysis. The flexible visual inspection concept is based on a systematic approach, that is able to increase the degree of flexibility and thus to decrease the set-up costs taking into account different type of data, positioning, occlusions and tolerances. The concept can be seen as "recipe" for solving industrial applications, stating at which stage, which kind of decisions have to be made. The visual inspection of analog display measuring instruments serves as a demonstration of this concept. The flexibility of the concept is demonstrated by testing the analysis process with the description of two instruments (a hygrometer and a clock), which is performed by adapting the analysis graph but without changing the detection algorithms. Since the detection is represented as detail relation in the analysis graph, a change of the detection algorithm is possible without changing the overall analysis. The separation of detection and analysis therefore ensures, that any existing pattern recognition software can be re-used.