Round Mark point positioning method based on connected region filtering

Abstract

A round Mark point positioning method based on connected region filtering relates to positioning methods. The round Mark point positioning method based on the connected region filtering mainly solves the problem that traditional round Mark point positioning methods are complex in positioning algorithm, high in computer memory requirements, low in detecting time, low in detecting accuracy and prone to being affected by external environments to lead to template matching failure, meanwhile, have high Mark process requirements and cannot meet the detecting accuracy requirements for deformed round Mark points. The method comprises firstly, calculating the ROI (region of interest) of a target Mark point; secondly, obtaining the edge of the target point; thirdly, obtaining a binary ROI image; fourthly, retaining the ROI connected region with the maximum area; fifthly, retaining the ROI background connected region with the maximum area; sixthly, designing a noise filter; seventhly, obtaining filtering Canny edge points; eighthly, obtaining the minimum enclosing rectangle; ninthly, removing Canny edge defects; lastly, obtaining the central and radial parameters of the round Mark point. The round Mark point positioning method based on the connected region filtering is applied to the field of positioning methods.

Description

technical field

[0001] The invention relates to a method for locating circular Mark points based on connected region filtering. Background technique

[0002] At present, machine vision is more and more widely used in industrial inspection. Among them, the positioning of the reference mark point (Mark point) is extremely important, and the accuracy and speed of its positioning directly affect the accuracy and speed of the product. The most commonly used Mark point at this stage is a circle, and the traditional positioning methods include template matching method, Hough circle transformation, contour positioning method, etc. The detection speed of the template matching method is fast, but it is easily affected by the external environment. Changes in illumination may cause unsuccessful matching with the standard template and affect the detection results; The demand is large, the execution speed is slow, and the process requirements for Mark are relatively high. For circular Ma...

Images