Research on Automatic Workpiece Sorting System Based on Machine Vision

This paper expounds the automatic recognition method of parts based on computer vision. The feature database of the processed parts is constructed by using machine learning method. Image preprocessing, threshold segmentation, edge and contour extraction are used to analyze the features of the image of the inspected part to judge whether the inspected part is qualified or not. Aiming at the attitude error generated when the workpiece is placed, a method for positioning the center of gravity and rotation angle of the workpiece based on boundary detection and contour tracking is proposed. Use the similarity measure to determine the characteristics of the object to be processed. Simulation results show that the method proposed in this paper is effective.