Research For Detecting The Rubber Ring Defects Based On Machine Vision

At present, the detecting of the surface defect and the measurement of the sealed rubber ring still relies on artificial inspection. It will increase the factory's labor cost and management cost, while the accuracy and speed of detection does not consistent with the production requirements. As for the inspection of an O-sealing defects and measure, the following aspects were studied and discussed in this thesis:Firstly, machine vision technology and rubber ring inspection technology were introduced, and a rubber ring vision inspection system was designed by adopting PC, acquisition card, camera and illumination system, and the picture of rubber ring was get successfully.Secondly, after comparing some classic arithmetic in digital image processing, Median Filter,threshold quantity dividing and Canny edge detection were chosen as the main arithmetic which had proved the efficiency and feasibility by lots of experiments.Thirdly, template matching and Hough Transform were adopted to compute the characteristic of the rubber ring,.Finally, error analysis was done,and the GUI was designed simply.