Sorting System of Liquor Packaging Labeling Based on Machine Vision
LI Zhijin
GAO Wei
JIANG Kaiqiang
LIU Zhongyang
Abstract：Aiming at the problem of low sorting efficiency of traditional liquor packaging labeling,this paper builds a sorting system based on machine vision.The system uses OpenCv open source visual library to design algorithm programs,collects packag-ing images through industrial cameras,preprocesses images,and extracts edge feature information of packaging images by dynamic threshold segmentation.The minimum circumscribed rectangle algorithm is used to locate the center coordinates of the image,and the ROI region of the main trademark is located.The similarity between the Hu moment characteristics of the main ROI edge of the trademark and the Hu moment characteristics of the main template is measured to identify the packaging trademark information.Then,the relatively offset auxiliary ROI region is located through the main trademark ROI region.According to the Hu moment char-acteristics of the auxiliary ROI region and the matching results of the auxiliary template,combined with the rotation angle of the min-imum circumscribed rectangle and the ratio of width to height,the 360°pose positioning of packaging is realized.The experimental results show that the system has fast response,the positioning accuracy reaches 0.8 mm,and the angle is controlled within 0.5°,which can meet the actual labeling sorting requirements.
Keywords：machine visionpositionHu momentminimum enclosing rectangle
Publication Date：2025-01-19
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：7( 45-50,83 )