Aiming at the problem that the precision and efficiency of concentric measurement of precise parts are not high

a precise parts concentric measurement system based on machine vision is designed. This system uses Halcon software to implement design of the algorithm

based on Canny edge detection

combined with bilinear interpolation to extract sub-pixel edges

and uses the least squares method to fit the circular contour. On the VS2015 platform

Halcon combined with the C# language to complete the system interface development to achieve high-precision

fast speed

non-contact concentric parameter detection of the sample. The experimental results show that the detection precision of the system can reach 10 μm

which can meet the actual needs.