Research on Boundary Detection for Turnout Rail Components Based on Machine Vision

Boundary detection is very important in the size measurement of the turnout rail components using machine vision. A new algorithm about boundary detection based on machine vision system is proposed. First an improved median filtering algorithm was used to noise reduction an image. Second Gabor operator energy diagram is generated. Then an elliptical-butterfly surround inhibition was designed to suppress the textures and enhance the boundary. Last a new binarization method and boundary detection algorithm is put forward according to the human beings visual observation. Experimental results show that the algorithm has good feasibility and effectiveness.