Product detection method based on machine vision

Abstract

The invention discloses a product detection method based on machine vision. The product detection method can achieve automatic detection of product defects by use of machine vision and template matching, locate the coordinates of defective products, control a mechanical arm to grab the unqualified products and to place the unqualified products in a disqualification area by a data acquisition card, and convey products passing through detection to the next workstation by a production line. The product detection method can achieve subtle high-precision detection of missing, deflection and parameter errors of such electronic components as resistors on a PCB, as well as status disqualification of a dial switch; through edge grabbing arrangement of the six-degrees-of-freedom mechanical arm, the detected unqualified products are automatically grabbed away from the production line to realize automation of the whole process; and in combination with matching and high-precision location of edge detection, the approximate positions of the products are found by matching at first, then the pixel coordinates and the angle of a corner of each cuboid product are determined via detection of two edges, the unqualified products are automatically grabbed out, and the product detection method is suitable for detecting different products.

Description

technical field [0001] The invention relates to a product detection technology, in particular to a machine vision detection method for missing parts, skew, parameter errors, and whether the status of a dial switch is correct, etc., and to control a mechanical arm grabbing method for electronic components such as resistors on a PCB. Background technique [0002] With the improvement of today's industrial production level, people have higher and higher requirements for product quality. When automatic production has become an inevitable trend, online detection technology occupies an increasingly important position in automatic production. In modern industrial automation production, product production is characterized by continuous mass production. Traditional manual inspection, while adding huge labor and management costs to the enterprise, still cannot guarantee 100% inspection rate (that is, "zero defect") ”), and the competition among enterprises today does not allow even ...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problems of low product detection accuracy and poor applicability in the prior art, and proposes a product detection method based on machine vision

Images