Part recognizing and sorting method and system based on machine vision

Abstract

The invention discloses a part recognizing and sorting method and system based on machine vision. Appearance detection and recognizing and sorting are combined, two mechanical arms are selected, one mechanical arm is used for collecting images, the other mechanical arm integrates a camera and a plurality of suction cups and is used for guiding, positioning and absorbing small parts, and the parts to be detected can be rapidly and accurately positioned and grasped. By means of the part recognizing and sorting method and system, detecting and sorting of various automobile parts in different sizes can be achieved, and the applicability is wider. The grasping programming difficulty of an ordinary mechanical arm for the different parts is lowered, and operability is high.

Description

technical field [0001] The invention relates to the field of component identification, in particular to a method and system for identifying and sorting components based on machine vision. Background technique [0002] With the rapid development of industry, the amount of labor is getting bigger and bigger. In the production process of sorting large quantities of parts, the quality, efficiency and accuracy of sorting parts by manpower are low, and it is difficult to meet industrial requirements. The detection method of machine vision can sort parts and components in large quantities, which greatly improves the production efficiency and automation of production. [0003] At present, the method of parts identification based on robot vision is mainly to install industrial cameras on both sides or above the conveyor belt, and collect images by taking pictures of the parts conveyed on the conveyor belt, or capture them by fixtures and manipulators before the camera for shooting, ...

AI Technical Summary

Problems solved by technology

[0008] The invention application with the application number 201610365672.1 "a multi-manipulator garbage sorting control system" uses a conveyor belt to transport garbage to the shooting area for processing and classification, and then sorts and places it by multiple robots. The dynamic shooting and imaging on the conveyor belt is suitable for the imaging of small garbage Unsatisfactory effect

[0009] In summary, only the camera is used to take pictures of the parts on the conveyor belt. For small parts, the imaging area is small, and the deviation of the parts on the conveyor belt and its own wear, scratches, lap cracking and other problems are easy to cause Industrial cameras miss or incompletely take pictures of small parts, and at the same time, the shooting effect of small parts is greatly affected by the moving state of the conveyor belt

Only use robotic claws or fixtures to grab the camera for shooting. For parts of different size ranges, different sizes of robotic claws or fixtures are required, which increases the cost

At the same time, the imaging area of ​​the component is small, and the gripping of the robot claw or fixture will interfere with its imaging and cause damage to the surface of the component

Images