WISEKO: a knowledge-based system for the recognition of 2D-complex objects in CAQ applications

The automatic recognition of complex objects (objects drilled in one or more places) represents a central scope of duties in the automation of numerous production processes. For such objects, further features must be determined and connected with each other to describe them. The number of drills, their forms as well as their normalized sizes must be determined and connected with each other. For industrial application in the field of automatic quality control (CAQ) and robotics the systems for the recognition of complex objects have to fulfil the requirement of flexibility and realtime processing. For this there are few suitable preprocessing methods for feature extraction, especially connected with the contour extraction and its description. Based on the object-oriented method for contour extraction (OCE), in this work the knowledge-based system for the recognition of complex objects called WISEKO will be introduced. The system is built up in form of an expert system and enables the recognition of any complex object. The WISEKO-system is flexible and can be used for various applications in CAQ and robotics. Because of using a hardware implementation for the OCE-method the WISEKO-system can be employed for realtime applications