Research on image segmentation of weld seam of oil derrick welded by arc welding robot

This paper puts forward a new method of PCNN (pulse-coupled neural networks) image segmentation, in which the binary matrix of the ignition frequency matrix is employed, for the first time, to act as the final result of image segmentation. It gives the principles of PCNN parameter selection under the guidance of this process. The new method reduces the dependence of PCNN on parameters, improves the effect of image segmentation, and produces good results after being applied to image recognition of weld seam of oil derrick welded by arc welding robot.