{"title":"Finding Picking Point Using Straight Line Detection of Label Attachment Machine","authors":"Lipheng Prum, Rutchanee Gullayanon, John Morris","doi":"10.1109/ICSEC56337.2022.10049335","DOIUrl":null,"url":null,"abstract":"We developed a new technique for detecting the position of labels using a SCARA Robot with the end-effector vacuum pad. The technique first found the image edge with a Canny detector, then selected straight lines and their intersections. It assumed that the label was basically rectangular in shape and roughly aligned so that the key edges were close to horizontal and vertical directions. The slope of the horizontal edge defined the rotational of the label. Otherwise, reducing the image tilting and the distortion by using a perspective transform matrix and thereafter converting the image coordinate into the SCARA robot coordinate. Through the factory environment, the experiment is conducted using various captured image conditions under a lighting source. The performance of the system provides the acceptable accuracy all of the picking coordinates with positioning errors, which x-coordinate are 0.01 – 0.25 mm, y-coordinate are 0.01 – 0.32 mm and rotation angle are 0.05° – 3.94°. In trials, the SCARA robot was able to grip the label precisely in each test.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"160 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 26th International Computer Science and Engineering Conference (ICSEC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSEC56337.2022.10049335","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
We developed a new technique for detecting the position of labels using a SCARA Robot with the end-effector vacuum pad. The technique first found the image edge with a Canny detector, then selected straight lines and their intersections. It assumed that the label was basically rectangular in shape and roughly aligned so that the key edges were close to horizontal and vertical directions. The slope of the horizontal edge defined the rotational of the label. Otherwise, reducing the image tilting and the distortion by using a perspective transform matrix and thereafter converting the image coordinate into the SCARA robot coordinate. Through the factory environment, the experiment is conducted using various captured image conditions under a lighting source. The performance of the system provides the acceptable accuracy all of the picking coordinates with positioning errors, which x-coordinate are 0.01 – 0.25 mm, y-coordinate are 0.01 – 0.32 mm and rotation angle are 0.05° – 3.94°. In trials, the SCARA robot was able to grip the label precisely in each test.