Computer vision for industrial inspection through linguistic fuzzy variable inputs

Computer vision systems have been used in a wide range of industrial visual inspection tasks. These applications are successful when problems can be well formulated. This paper describes the implementation of a visual inspection system which formulate the human expertise in terms of fuzzy rules. This method is well applicable when an inspection task can not be numerically defined. Commencing with the basic system introduction, the paper will illustrate practical application example where IC mark (often in the forms of English characters and a company logo) inspection process is elaborated