The research of material sorting system based on Machine Vision

摘要

With the expansion of enterprise production scale and the increase of labor cost, robots, including robots, are more and more involved in the production process. Sorting is an important part of the enterprise production process. In the sorting system, if the robot's grasping is not accurate, it is easy to cause the grab failure, seriously reduce the production efficiency, and even cause the damage of the grab sample <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">°</sub> Aiming at the problem of grasping accuracy of manipulator, a sorting system composed of machine vision, PLC, robot and assembly line is constructed. In the process of image processing, local threshold segmentation, edge detection and support vector machine recognition are used. The position and pose information of the sample is processed by PLC and then transmitted to the robot. The experimental results show that the robot can accurately locate and grasp the samples, which has high engineering practice value and guiding significance.