depth and height-difference of key assembly parts of high-speed rail carriage
a non-contact assembly quality detection method based on machine vision is proposed.Firstly
a adaptive window median filter is designed for suppressing the salt-pepper noise.Secondly
a subpixel centralline stripe is extracted using the algorithm of ridge line tracking and Hession matrix.Then
the assembly feature is measured by the mapping relationship between the pixel coordinate system and the physical coordinate system.The experimental results show that the detection accuracy of the method reaches 0.05 mm.