Multi-material rapid comparison and matching method for production line

Abstract

A multi-material rapid comparison and matching method for a production line is characterized by specifically comprising the following steps that firstly, the types, the number and the placing positions of materials placed on each material tray are determined; 2, various material trays are manufactured, each tray comprises a plurality of rectangular grooves, and the size and the depth of the grooves are matched with those of materials; 3, various types of materials are correctly placed in the rectangular groove of the tray, and an industrial camera installed above the tray shoots a whole tray image and reserves the whole tray image as a template; each material tray is provided with a template; 4, on the production line, a material comparison and matching system collects a material tray image, Hough transformation is carried out on the material tray image to obtain a rectangular groove image, the groove image is segmented through an automatic watershed marking method, and a material image is extracted. According to the invention, hundreds of materials on the material tray can be quickly and reliably identified.

Description

technical field [0001] The invention relates to the field of machine vision, in particular to a material matching method for a production line. Background technique [0002] On the production line, often a production process requires the supply of dozens or even hundreds of materials, and the types and sizes of these materials vary. If the matching of materials is wrong, the production impact on the production line is huge. [0003] At present, the most commonly used method is to conduct neural network training and identification of materials through machine vision systems to detect whether the matching of materials is correct. The current method has the following problems: [0004] 1. The pixel size of the material in the image has a great impact on the recognition rate. For large-sized materials, the neural network method can have a high recognition rate, and small ones such as screws and nuts have a low recognition rate. [0005] 2. It cannot correctly identify materia...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to provide a multi-material rapid comparison and matching method used in the production line to overcome the defects of the prior art machine vision system for neural network training and low recognition accuracy of materials

Images