Development of part contour recognition system based on edge detection
                                    XU Xinjie1, WANG Xiufeng2, LU Wenqi1, YOU Wenhui1, WU Di1, YANG Liangliang1
(1.Faculty of Mechanical Engineering & Automation, Zhejiang SciTech Universi, Hangzhou 310018, China;2.Hangzhou Qi Xing Robot Technology Co.,Ltd., Hangzhou 310018, China)

Abstract: Aiming at the problems of high cost and low efficiency in industrial pipeline detection, the contour detection technology was applied to industrial pipeline detection. Based on the analysis of the basic principle of edge detection method, a method of part contour recognition based on edge detection was proposed. The method firstly used Canny edge detection algorithm to extract the edge of the part, and then further extracted the related features of the part contour. Finally, by comparing with the contour features of the part to be detected, the recognition and detection of the part can be realized. In order to verify the correctness of the design method, a part contour recognition system was built, and the performance of the system was tested by industrial parts. The results show that the system can quickly and accurately identify the target parts, meet the needs of industrial pipeline inspection.

Key words: industrial pipeline detection; edge detection; contour recognition; Canny algorithm