Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/11461
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKozlenko, Mykola-
dc.contributor.authorSendetskyi, Volodymyr-
dc.contributor.authorSimkiv, Oleksiy-
dc.contributor.authorSavchenko, Nazar-
dc.contributor.authorBosyi, Andrii-
dc.contributor.authorКозленко, Микола Іванович-
dc.date.accessioned2021-12-13T07:44:20Z-
dc.date.available2021-12-13T07:44:20Z-
dc.date.issued2021-01-28-
dc.identifier.citationM. Kozlenko, V. Sendetskyi, O. Simkiv, N. Savchenko, and A. Bosyi, "Identity documents recognition and detection using semantic segmentation with convolutional neural network," in CEUR Workshop Proceedings, vol. 2923, Kyiv, Ukraine, Jan. 28, 2021, pp. 234-242, doi: 10.5281/zenodo.5758182uk_UA
dc.identifier.issn1613-0073-
dc.identifier.other10.5281/zenodo.5758182-
dc.identifier.urihttp://ceur-ws.org/Vol-2923/paper25.pdf-
dc.identifier.urihttp://hdl.handle.net/123456789/11461-
dc.description.abstractObject recognition and detection are well-studied problems with a developed set of almost standard solutions. Identity documents recognition, classification, detection, and localization are the tasks required in a number of applications, particularly, in physical access control security systems at critical infrastructure premises. In this paper, we propose the new original architecture of a model based on an artificial convolutional neural network and semantic segmentation approach for recognition and detection of identity documents in images. The challenge with the processing of such images is the limited computational performance and the limited amount of memory when such an application is running on industrial one-board microcomputer hardware. The aim of this research is to prove the feasibility of the proposed technique and to obtain quality metrics. The methodology of the research is to evaluate the deep learning detection model trained on the mobile identity document video dataset. The dataset contains five hundred video clips for fifty different identity document types. The numerical results from simulations are used to evaluate the quality metrics. We present the results as accuracy versus threshold of the intersection over union value. The paper reports the accuracy above 0.75 for the intersection over union (IoU) threshold value of 0.8. Besides, we assessed the size of the model and proved the feasibility of running the model on industrial one-board microcomputer or smartphone hardware.uk_UA
dc.language.isoen_USuk_UA
dc.publisherCEUR-WSuk_UA
dc.relation.ispartofseriesCEUR Workshop Proceedings;-
dc.subjectidentity documentuk_UA
dc.subjectobject detectionuk_UA
dc.subjectsemantic segmentationuk_UA
dc.subjectdocument recognitionuk_UA
dc.subjectdocument classificationuk_UA
dc.subjectdeep learninguk_UA
dc.subjectneural networkuk_UA
dc.titleIdentity documents recognition and detection using semantic segmentation with convolutional neural networkuk_UA
dc.typeArticleuk_UA
Appears in Collections:Статті та тези (ФМІ)

Files in This Item:
File Description SizeFormat 
paper25.pdf1.39 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.