Part surface burr detection method based on machine vision

Abstract

The invention relates to a part surface burr detection method based on machine vision. The part surface burr detection method comprises the following steps: S1) acquiring a to-be-detected image and a template image; s2) respectively performing image processing on the to-be-detected image and the template image to obtain a to-be-detected contour and a template contour; s3) drawing a connected domain between the to-be-detected contour and the template contour, and solving the shortest linear distance from each contour point of the to-be-detected contour to the template contour and the corresponding shortest distance point; s4) judging whether a connecting line between each contour point and the corresponding shortest distance point completely falls in the connected domain; s5) calculating the minimum distance from each contour point to the corresponding shortest distance point along a certain path in the connected domain, and taking the minimum distance as the internal distance of each contour point; and S6) comparing the internal distance of each contour point, identifying whether each contour point is an abnormal point or not, and analyzing all the abnormal points to obtain surface burr information of the to-be-detected part.

Description

technical field [0001] The invention belongs to the technical field of burr detection, in particular to a method for detecting surface burrs of parts and components based on machine vision. Background technique [0002] Burrs refer to the excess parts that are not smooth and uneven on the edge, surface or smoother plane of a component for some reason. The existence of burrs will not only affect its quality, but may also cause it to fail to work properly, resulting in reduced reliability and stability, and the shedding of burrs will even cause premature wear of the sliding surface of the machine and increase in noise, resulting in machine stuck, Operation failure and other safety hazards. [0003] At present, the detection methods of burrs on the surface of parts are mainly divided into two types: manual detection and equipment detection. In the prior art, most of them adopt manual detection methods such as wire hanging method, magnification method, hand touch and naked eye...

AI Technical Summary

Problems solved by technology

In the prior art, most of them use artificial detection methods such as wire hanging method, magnification method, hand touch and naked eye identification, which mainly rely on manual judgment. It causes fatigue, the speed of manual detection is far less than that of machine detection, the detection efficiency is low, and there are often problems of missed detection and wrong detection; a few use special equipment mainly based on sensors and optical microscopes for detection, for example, Use an optical coordinate measuring machine to measure the shape, height, length and other related parameters of the burr, but its measurement speed is slow, it takes a lot of time to measure, and it is difficult to meet the needs of modern production

Images