Show simple item record

dc.contributor.authorBereciartua-Perez, Arantza
dc.contributor.authorDuro, Gorka
dc.contributor.authorEchazarra, Jone
dc.contributor.authorGonzález, Francico Javier
dc.contributor.authorSerrano, Alberto
dc.contributor.authorIrizar, Liher
dc.date.accessioned2022-11-29T10:37:31Z
dc.date.available2022-11-29T10:37:31Z
dc.date.issued2022-11-04
dc.identifier.citationBereciartua-Perez, Arantza, Gorka Duro, Jone Echazarra, Francico Javier González, Alberto Serrano, and Liher Irizar. 2022. "Deep Learning-Based Method for Accurate Real-Time Seed Detection in Glass Bottle Manufacturing" Applied Sciences 12, no. 21: 11192. https://doi.org/10.3390/app122111192en
dc.identifier.urihttp://hdl.handle.net/11556/1442
dc.description.abstractGlass bottle-manufacturing companies produce bottles of different colors, shapes and sizes. One identified problem is that seeds appear in the bottle mainly due to the temperature and parameters of the oven. This paper presents a new system capable of detecting seeds of 0.1 mm2 in size in glass bottles as they are being manufactured, 24 h per day and 7 days per week. The bottles move along the conveyor belt at 50 m/min, at a production rate of 250 bottles/min. This new proposed method includes deep learning-based artificial intelligence techniques and classical image processing on images acquired with a high-speed line camera. The algorithm comprises three stages. First, the bottle is identified in the input image. Next, an algorithm based in thresholding and morphological operations is applied on this bottle region to locate potential candidates for seeds. Finally, a deep learning-based model can classify whether the proposed candidates are real seeds or not. This method manages to filter out most of false positives due to stains in the glass surface, while no real seeds are lost. The F1 achieved is 0.97. This method reveals the advantages of deep learning techniques for problems where classical image processing algorithms are not sufficient.en
dc.description.sponsorshipThis work was partially supported by OPENZDM project. This is a project from the European Union’s Horizon Europe research and innovation programme under Grant Agreement No. 101058673 in the call HORIZON-CL4-2021-TWIN-TRANSITION-01en
dc.language.isoengen
dc.publisherMultidisciplinary Digital Publishing Institute (MDPI)en
dc.rightsAttribution 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.titleDeep Learning-Based Method for Accurate Real-Time Seed Detection in Glass Bottle Manufacturingen
dc.typearticleen
dc.identifier.doi10.3390/app122111192en
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/H2020/101058673/EU/An open platform for realising zero defect in cyber-physical manufacturing/OPENZDMen
dc.rights.accessRightsopenAccessen
dc.subject.keywordsSeeds countingen
dc.subject.keywordsQuality controlen
dc.subject.keywordsDeep learningen
dc.subject.keywordsImage processingen
dc.subject.keywordsObject detectionen
dc.subject.keywordsClassificationen
dc.subject.keywordsReal-time controlen
dc.identifier.essn2076-3417en
dc.issue.number21en
dc.journal.titleApplied Sciencesen
dc.page.initial11192en
dc.volume.number12en


Files in this item

Thumbnail

    Show simple item record

    Attribution 4.0 InternationalExcept where otherwise noted, this item's license is described as Attribution 4.0 International