Visual inspection system for automatic connector producing machines

Abstract

Today’s high speed complex manufacturing systems require the development of automation technologies that can be effectively integrated into the system and use in manufacturers process. This paper proposes a new method for inspecting the order of electrical colored wires in industrial connector cables manufacture. The system is able to check the difference in the color, number of wires, and color sequence cables connector with the self-designing model. The system learns the model cable and then it can automatically inspect each cable assembly by machine. The key ideas of the algorithm are threefold: first, the rectangle connector parts of sample image and test image of product are analyzed and detected by using shape and region properties. The region of connectors are then extracted and rectified to vertical direction. Second, a robust segmentation algorithm for extracting wires from images even if they are strongly bent and partially overlapped. Third, a color recognition algorithm is able to cope with highlights and shadows. To verify the efficiency and effectiveness of the proposed method for color wires inspection, the authors report the system evaluation by many different samples with a variety of conditions. The representation of a strong point of this system is reliable method for extracting wire regions and analyzing color wire.