Machine vision inspection of VF display boards

This paper describes our research in developing computer vision algorithms for inspecting vacuum fluorescent (VF) displaying boards. The entire system consists of two major procedures, learning and inspection. The learning procedure is applied to every new type of VF boards and produces a symbolic list of specification for the inspection procedure. For every VF board on the production line, the inspection procedure will generate pass or fail signal based on the image analysis of various test patterns. At the same time, the inspection procedure also save the image that contains the defect evidence for further verification