Research on Sub-pixel Precision Dimension Measurement of Rotor Punching Based on Machine Vision
Aiming at the low efficiency and difficulty of traditional manual dimension measurement for stamped parts,a sub-pixel precision dimension measurement method for rotor punching based on machine vision is proposed.Firstly,this method is used to gray the collected image,and then the median filter is applied to reduce the noise interference.The adaptive threshold edge detection is re-alized through the combination of the Canny operator and Otsu method,and the improved Zernike moment method is used for the sub-pixel positioning to obtain the sub-pixel coordinates.Then,the contour segmentation algorithm is designed to mainly extract the sub-pixel contour of the inner and outer circles.At the same time,the interesting region is arranged to segment the outline of the frame-work line segment based on the K-Means clustering algorithm.Finally,the least squares fitting method is used to solve the diameter of inner and outer circles of the rotor punching and the framework interval size.The experimental results show that the measurement accuracy of this method can reach 0.01 mm,and it has the high measurement accuracy and rapid speed and high practical value.
万方数据
维普
