Research on visual inspection algorithm of PET bottle cap defects
                                                    WU Lan lan1, CHEN Shuo1, HUANG Xiang bin1, LU Hua2
（1.School of Mechanical Engineering and Automation, Fuzhou University, Fuzhou 350116, China;2.Fuzhou Sunlong Ink Jet Printing Technology Co., Ltd., Fuzhou 350014, China）


Abstract: Aiming at the problems of defects in PET bottle capping production line, a detection algorithm based on machine vision technology was proposed. Firstly, the hardware platform of the system was built, so that the detection difficulties were analyzed. The template matching algorithm was introduced to detect the presence or absence of the cap, and the regions of the embryo ring and upper edge of the cap were positioned from the matching results. Then, the Harris corner detection algorithm was used to fit the straight line of the embryo ring. Furthermore, the Canny algorithm and the least squares algorithm were used to fit the straight line of upper edge of the cap. Finally, by calculating the angle and distance between the line of upper edge of the cap and the reference line, the defects of inclined cap and high cap were categorized. The results indicate that the detection algorithm has great detection result and efficient real time processing efficiency, with the detection accuracy up to 99%, the detection efficiency is less than 100ms.
Key words: PET bottle cap defects; machine vision; template matching; harris corner detection; linear fitting