Qi Huan, Hongyu Yi, Daolin Qu, Chunyuan Wang, Dianchun Bai
{"title":"A Fault Detection Method Based on SIFT Algorithm","authors":"Qi Huan, Hongyu Yi, Daolin Qu, Chunyuan Wang, Dianchun Bai","doi":"10.1109/ICECIE52348.2021.9664688","DOIUrl":null,"url":null,"abstract":"This paper, based on an improved SIFT algorithm, is applied to the vision system of a plug-in machine. The purpose is to judge whether a part of the component to be inserted is damaged or deflected. SIFT algorithm has many good characteristics, but there are a lot of redundant points and mismatched points in the matching results. In this paper, an improved SIFT algorithm is proposed, and a more simple and intuitive method is adopted to filter out a large number of redundant points and mismatched points in the SIFT feature matching results, which is applied to the special case of insert machine to identify the damage and deflection Angle of a part of the component.","PeriodicalId":309754,"journal":{"name":"2021 3rd International Conference on Electrical, Control and Instrumentation Engineering (ICECIE)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 3rd International Conference on Electrical, Control and Instrumentation Engineering (ICECIE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICECIE52348.2021.9664688","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
This paper, based on an improved SIFT algorithm, is applied to the vision system of a plug-in machine. The purpose is to judge whether a part of the component to be inserted is damaged or deflected. SIFT algorithm has many good characteristics, but there are a lot of redundant points and mismatched points in the matching results. In this paper, an improved SIFT algorithm is proposed, and a more simple and intuitive method is adopted to filter out a large number of redundant points and mismatched points in the SIFT feature matching results, which is applied to the special case of insert machine to identify the damage and deflection Angle of a part of the component.