Vis enkel innførsel

dc.contributor.authorHuang, Zihao
dc.contributor.authorXiao, Hong
dc.contributor.authorZhang, Rongyue
dc.contributor.authorWang, Hao
dc.contributor.authorZhang, Cheng
dc.contributor.authorShi, Xiucong
dc.date.accessioned2019-12-03T12:23:58Z
dc.date.available2019-12-03T12:23:58Z
dc.date.created2019-12-02T15:09:42Z
dc.date.issued2019
dc.identifier.isbn978-1-7281-2980-8
dc.identifier.urihttp://hdl.handle.net/11250/2631505
dc.description.abstractThe traditional defect detection algorithms based on image registration, image contrast and other image processing algorithms are only limited to a single defect. Though deep-learning-based object detection algorithms can be used to detect a variety of different defects, the state-of-the-art deep-learning-based object detection algorithms still have low detection accuracy on small size defects. Basing on Cascade R-CNN in this paper, a new multi-scale feature extraction method-the Multi-Scale Feature Pair-is proposed and is used to establish a defect detection model for metal can products of an enterprise. Experimental results show that the accuracy (AP@0.5) of our improved model is 6.1% higher than Cascade R-CNN.nb_NO
dc.language.isoengnb_NO
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)nb_NO
dc.relation.ispartof2019 IEEE International Congress on Cybermatics
dc.titleMulti-Scale Feature Pair Based R-CNN Method for Defect Detectionnb_NO
dc.typeChapternb_NO
dc.description.versionacceptedVersionnb_NO
dc.source.pagenumber46-51nb_NO
dc.identifier.doihttps://doi.org/10.1109/iThings/GreenCom/CPSCom/SmartData.2019.00031
dc.identifier.cristin1755558
dc.description.localcode© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.nb_NO
cristin.unitcode194,63,10,0
cristin.unitnameInstitutt for datateknologi og informatikk
cristin.ispublishedtrue
cristin.fulltextpostprint


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel