Kaifu Zhang, Yihui Li, Y. Guan, Li He, Yuxi Gan, Zhenjiang Dong
{"title":"奇形部件的视觉检测系统","authors":"Kaifu Zhang, Yihui Li, Y. Guan, Li He, Yuxi Gan, Zhenjiang Dong","doi":"10.1109/ROBIO.2018.8664867","DOIUrl":null,"url":null,"abstract":"This paper presents a locating method that combines traditional threshold segmentation, feature information extraction and edge contour fitting to detect and locate odd-form components and PCB holes. Feature extraction, instead of a template matching algorithm, is used to improve the robustness of recognition in this method. The deviation in the edge unsmoothness caused by the initial edge contour is solved using an edge contour fitting technique. Finally, experiments are designed and performed to verify the precision of the odd-form components, and the PCB holes detection and correction system.","PeriodicalId":417415,"journal":{"name":"2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"A Vision Detection System for Odd-Form Components\",\"authors\":\"Kaifu Zhang, Yihui Li, Y. Guan, Li He, Yuxi Gan, Zhenjiang Dong\",\"doi\":\"10.1109/ROBIO.2018.8664867\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents a locating method that combines traditional threshold segmentation, feature information extraction and edge contour fitting to detect and locate odd-form components and PCB holes. Feature extraction, instead of a template matching algorithm, is used to improve the robustness of recognition in this method. The deviation in the edge unsmoothness caused by the initial edge contour is solved using an edge contour fitting technique. Finally, experiments are designed and performed to verify the precision of the odd-form components, and the PCB holes detection and correction system.\",\"PeriodicalId\":417415,\"journal\":{\"name\":\"2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)\",\"volume\":\"46 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ROBIO.2018.8664867\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ROBIO.2018.8664867","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
This paper presents a locating method that combines traditional threshold segmentation, feature information extraction and edge contour fitting to detect and locate odd-form components and PCB holes. Feature extraction, instead of a template matching algorithm, is used to improve the robustness of recognition in this method. The deviation in the edge unsmoothness caused by the initial edge contour is solved using an edge contour fitting technique. Finally, experiments are designed and performed to verify the precision of the odd-form components, and the PCB holes detection and correction system.