{"title":"Cylindrical product label image stitching method","authors":"Jiaming Xu, Conggui Chen, Hongwei Xie, Fan Lu","doi":"10.1109/CIAPP.2017.8167233","DOIUrl":null,"url":null,"abstract":"In order to solve the difficult problem of splicing as a result of cylindrical distortion, this paper presents a method of image stitching of cylindrical products based on four camera calibration assessment model. The internal parameters and pose of each camera are used to correct the image by calibrating the four cameras placed in increments of 90 degrees around the cylindrical product. Further, a 3D cylindrical distortion correction model is created to deal with the distortion information on the cylindrical product label. Finally, the pixel points on the model are projected onto the 2D image to be spliced to reconstruct the whole label. The experimental results show that the processing speed is 98ms per whole label image which contains 4 images with resolution 1280×1024 and error rate of splicing is 0.315%.","PeriodicalId":187056,"journal":{"name":"2017 2nd IEEE International Conference on Computational Intelligence and Applications (ICCIA)","volume":"70 6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 2nd IEEE International Conference on Computational Intelligence and Applications (ICCIA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CIAPP.2017.8167233","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4
Abstract
In order to solve the difficult problem of splicing as a result of cylindrical distortion, this paper presents a method of image stitching of cylindrical products based on four camera calibration assessment model. The internal parameters and pose of each camera are used to correct the image by calibrating the four cameras placed in increments of 90 degrees around the cylindrical product. Further, a 3D cylindrical distortion correction model is created to deal with the distortion information on the cylindrical product label. Finally, the pixel points on the model are projected onto the 2D image to be spliced to reconstruct the whole label. The experimental results show that the processing speed is 98ms per whole label image which contains 4 images with resolution 1280×1024 and error rate of splicing is 0.315%.